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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 1112
    Prev
    Next
    INDEX
    Explanations

    mentions and discussions related to political and economic sanctions

    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
    288
    +0.31
    1.0%
    35
    +0.15
    0.5%
    386
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.31
    0.08
    524
    +0.15
    0.05
    472
    +0.14
    0.04
    Negative Logits
    swick
    -1.50
    WORK
    -1.14
    ullivan
    -1.10
    uscript
    -1.09
    lihood
    -1.08
    Values
    -1.04
    OWN
    -1.04
    erd
    -1.03
    ITNESS
    -1.03
    ortun
    -1.00
    POSITIVE LOGITS
     relief
    1.56
     levied
    1.41
     imposed
    1.34
     sanctions
    1.27
     regimes
    1.26
     targeting
    1.18
     regime
    1.18
     cooker
    1.13
     embargo
    1.09
     restricting
    1.04
    Activations Density 0.820%

    No Known Activations