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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 7980
    Prev
    Next
    INDEX
    Explanations

    information related to international affairs, policies, and political actions

    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
    393
    +0.19
    1.0%
    640
    +0.16
    0.8%
    123
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    123
    +0.19
    0.19
    22
    +0.16
    0.17
    29
    +0.11
    0.17
    Negative Logits
    CLASSIFIED
    -0.72
    ratulations
    -0.65
    catentry
    -0.65
    Voice
    -0.63
    NOW
    -0.63
     surpr
    -0.63
    bol
    -0.63
    ãĤ³
    -0.62
    tal
    -0.62
     %%
    -0.61
    POSITIVE LOGITS
     accordance
    1.27
     lieu
    1.25
     conjunction
    1.22
     favor
    1.14
     vitro
    1.11
    effic
    1.10
    efficiency
    1.08
     order
    1.03
     spite
    1.03
     favour
    1.02
    Activations Density 2.183%

    No Known Activations