© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 33171
    Prev
    Next
    INDEX
    Explanations

    content related to terrorism and political 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
    420
    +0.16
    0.6%
    345
    +0.13
    0.5%
    194
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    149
    +0.16
    0.06
    724
    +0.13
    0.19
    252
    +0.12
    0.12
    Negative Logits
    trial
    -0.81
     afterward
    -0.75
     sanity
    -0.75
    Fix
    -0.72
    ignore
    -0.72
    igslist
    -0.72
     beforehand
    -0.70
     afterwards
    -0.69
    plet
    -0.69
    draft
    -0.68
    POSITIVE LOGITS
    quartered
    1.21
     synonymous
    1.01
     Serving
    1.01
     Located
    0.99
    ablished
    0.97
     unparalleled
    0.94
     renowned
    0.90
    Located
    0.88
     worldwide
    0.88
     headquartered
    0.87
    Activations Density 17.542%

    No Known Activations