© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 32426
    Prev
    Next
    INDEX
    Explanations

    information related to physical and mechanical pressure, such as in engines, machinery, and medical conditions like hypertension and blood pressure

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.15
    0.8%
    635
    +0.11
    0.6%
    19
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    328
    +0.15
    0.06
    635
    +0.11
    0.08
    724
    +0.09
    0.13
    Negative Logits
    roma
    -0.73
    naissance
    -0.73
    nam
    -0.73
    nen
    -0.67
    alian
    -0.66
    zbollah
    -0.65
    friend
    -0.65
    rum
    -0.64
    endez
    -0.64
    beard
    -0.64
    POSITIVE LOGITS
     cooker
    1.03
     exerted
    0.75
     gradient
    0.73
     differential
    0.72
     pressure
    0.68
     pressures
    0.66
    urized
    0.65
     ventilation
    0.62
     presses
    0.62
     Sodium
    0.61
    Activations Density 9.063%

    No Known Activations