© 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
    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. 3720
    Prev
    Next
    INDEX
    Explanations

    questions or descriptions related to social, political, and global issues

    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
    451
    +0.15
    0.5%
    463
    +0.14
    0.5%
    55
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    55
    +0.15
    0.07
    566
    +0.14
    0.06
    463
    +0.14
    0.06
    Negative Logits
    ooters
    -1.00
    teness
    -0.96
    naissance
    -0.90
    actionDate
    -0.87
    ancial
    -0.86
    osi
    -0.84
    allery
    -0.83
    ooter
    -0.83
    isoft
    -0.80
     Mechanics
    -0.79
    POSITIVE LOGITS
    ?),
    1.01
    ?",
    0.94
     actually
    0.92
    ?)
    0.91
    ?"
    0.87
    opter
    0.86
    ?]
    0.86
    ?
    0.86
     dom
    0.86
     anat
    0.84
    Activations Density 1.038%

    No Known Activations