© 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. 3705
    Prev
    Next
    INDEX
    Explanations

    references to things being on par or equal to something else

    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
    724
    +0.16
    0.6%
    236
    +0.14
    0.5%
    526
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    187
    +0.16
    0.03
    251
    +0.14
    0.03
    389
    +0.13
    0.03
    Negative Logits
    士
    -0.94
    ACTED
    -0.92
    ħĭ
    -0.91
    ORTS
    -0.91
    ãĥ¼ãĥĨãĤ£
    -0.88
    furt
    -0.86
    OME
    -0.86
    schild
    -0.85
    terday
    -0.84
     Rasmussen
    -0.84
    POSITIVE LOGITS
    ishes
    1.05
    amount
    1.03
     ILCS
    1.01
    ishment
    1.00
    ison
    0.95
    aps
    0.95
    icularly
    0.93
    isher
    0.92
    aff
    0.92
    rots
    0.91
    Activations Density 0.240%

    No Known Activations