© 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 EvalsExportsAPI 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. 33732
    Prev
    Next
    INDEX
    Explanations

    references to opposition or conflict

    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
    +0.14
    0.7%
    393
    +0.12
    0.6%
    25
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.14
    0.16
    393
    +0.12
    0.29
    635
    +0.11
    0.09
    Negative Logits
    ornia
    -0.66
    ATURES
    -0.65
    Ut
    -0.65
    ffe
    -0.64
    ayette
    -0.64
    ATURE
    -0.63
    enough
    -0.62
    RIC
    -0.61
    OGR
    -0.60
    sufficient
    -0.60
    POSITIVE LOGITS
     backdrop
    1.39
     perceived
    0.74
     intruder
    0.73
     wall
    0.73
     invaders
    0.73
     opponent
    0.73
     evils
    0.73
     extremes
    0.73
     prejudice
    0.70
     landlord
    0.68
    Activations Density 15.354%

    No Known Activations