© 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. 1439
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific location, "Grenfell Tower"

    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
    624
    +0.10
    0.6%
    195
    +0.09
    0.6%
    152
    +0.08
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.10
    0.07
    232
    +0.09
    0.04
    624
    +0.08
    0.03
    Negative Logits
    illary
    -0.54
     Seym
    -0.53
    OTO
    -0.51
    ULAR
    -0.51
    Republic
    -0.50
    BIL
    -0.50
    anwhile
    -0.49
    vP
    -0.49
    GO
    -0.48
    DAQ
    -0.48
    POSITIVE LOGITS
    owship
    1.11
    nesday
    0.63
    erers
    0.62
    fell
    0.61
    mere
    0.56
    ows
    0.55
    hardt
    0.53
    lict
    0.53
    erer
    0.51
    borough
    0.50
    Activations Density 0.608%

    No Known Activations