Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 45278
    Prev
    Next
    INDEX
    Explanations

    messages related to social issues and advocacy

    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
    +0.31
    1.3%
    224
    +0.12
    0.5%
    217
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.31
    0.28
    142
    +0.12
    0.12
    77
    +0.11
    0.08
    Negative Logits
    ords
    -0.72
    endars
    -0.72
    engeance
    -0.70
    ENCY
    -0.70
    fac
    -0.69
    erenn
    -0.69
    Boss
    -0.68
    umbers
    -0.68
    essors
    -0.67
    ced
    -0.66
    POSITIVE LOGITS
     message
    1.14
     messages
    1.03
    message
    0.94
     conveyed
    0.93
     Messages
    0.93
    posts
    0.92
    FontSize
    0.84
     Message
    0.80
    ieu
    0.79
     reson
    0.78
    Activations Density 12.239%

    No Known Activations