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. 45256
    Prev
    Next
    INDEX
    Explanations

    questions and statements related to political and social issues

    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
    640
    +0.26
    1.2%
    447
    +0.24
    1.0%
    160
    +0.15
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.26
    0.55
    160
    +0.24
    0.34
    6
    +0.15
    0.26
    Negative Logits
     migr
    -0.77
     migration
    -0.76
     breached
    -0.75
     upstream
    -0.75
    emed
    -0.72
     herb
    -0.71
     negoti
    -0.70
    acan
    -0.70
     stret
    -0.68
     nightly
    -0.67
    POSITIVE LOGITS
    Answer
    1.66
    ?????-?????-
    1.19
     Answer
    1.17
    Yes
    1.09
    YES
    1.08
    Reference
    1.07
    Well
    1.02
    ?????-
    1.01
    Trivia
    0.99
    ANS
    0.98
    Activations Density 12.881%

    No Known Activations