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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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 E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 4653
    Prev
    Next
    INDEX
    Explanations

    mentions related to law enforcement activities, criminal activity, and international organizations such as NATO and ICE

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    343
    +0.17
    0.6%
    288
    +0.15
    0.6%
    326
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.17
    0.18
    343
    +0.15
    0.14
    326
    +0.15
    0.12
    Negative Logits
    uns
    -1.07
     Wu
    -0.93
    semble
    -0.92
     Jah
    -0.92
    ths
    -0.86
    hood
    -0.83
    ysis
    -0.82
    lass
    -0.81
    leon
    -0.80
     Gore
    -0.79
    POSITIVE LOGITS
    EMENT
    0.90
    BIL
    0.88
    IS
    0.86
    ®
    0.85
    CC
    0.84
     Headquarters
    0.84
    ipedia
    0.82
    ICE
    0.80
    HS
    0.80
    IDE
    0.79
    Activations Density 2.244%

    No Known Activations