© 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. 32285
    Prev
    Next
    INDEX
    Explanations

    phrases related to past actions or states

    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
    +0.19
    0.9%
    718
    +0.15
    0.7%
    339
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.19
    0.26
    393
    +0.15
    0.30
    640
    +0.11
    0.27
    Negative Logits
    essional
    -0.70
    edIn
    -0.69
    Choice
    -0.64
    sequence
    -0.63
     Compass
    -0.63
    uve
    -0.61
    ulus
    -0.61
    mentation
    -0.60
    relevant
    -0.59
    stakes
    -0.59
    POSITIVE LOGITS
     shrink
    0.75
     haunt
    0.74
     stomp
    0.71
     advertise
    0.70
     crush
    0.69
     treat
    0.69
     numbering
    0.68
     wait
    0.66
     scoop
    0.66
     rack
    0.66
    Activations Density 13.999%

    No Known Activations