© 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. 5388
    Prev
    Next
    INDEX
    Explanations

    words related to mistakes or misunderstandings

    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
    35
    +0.16
    0.5%
    746
    +0.16
    0.5%
    503
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    35
    +0.16
    0.04
    251
    +0.16
    0.04
    57
    +0.13
    0.04
    Negative Logits
    hetti
    -1.14
    ieri
    -0.93
     Yards
    -0.89
    INGS
    -0.89
    ¯¯¯¯
    -0.88
    ¯¯
    -0.88
    iaries
    -0.86
    ï¸
    -0.85
    loo
    -0.85
     Parties
    -0.85
    POSITIVE LOGITS
    cellaneous
    1.67
    appropri
    1.49
    pell
    1.40
    pelled
    1.38
    aligned
    1.25
    per
    1.20
    behavior
    1.20
    informed
    1.19
    beh
    1.19
    ceived
    1.18
    Activations Density 1.136%

    No Known Activations