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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 13476
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal and political controversies

    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%
    160
    +0.12
    0.6%
    342
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    160
    +0.15
    0.19
    308
    +0.12
    0.11
    154
    +0.10
    0.14
    Negative Logits
    erest
    -0.62
     mum
    -0.57
     ling
    -0.56
     mall
    -0.55
     level
    -0.54
    jured
    -0.54
     comfort
    -0.53
    ricular
    -0.53
    earch
    -0.52
     lull
    -0.52
    POSITIVE LOGITS
    including
    1.07
    which
    1.03
    something
    1.02
    meaning
    0.97
    particularly
    0.97
    perhaps
    0.96
    especially
    0.95
     namely
    0.94
    possibly
    0.93
    even
    0.93
    Activations Density 6.879%

    No Known Activations