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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 1522
    Prev
    Next
    INDEX
    Explanations

    expressions of comparison or uncertainty

    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
    +0.18
    0.7%
    92
    +0.14
    0.6%
    718
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    484
    +0.18
    0.06
    284
    +0.14
    0.06
    578
    +0.13
    0.04
    Negative Logits
    ADVERTISEMENT
    -0.82
    ĸļ
    -0.80
    wagen
    -0.78
     Peaks
    -0.74
    CHR
    -0.73
    ATTLE
    -0.72
    GREEN
    -0.71
     robber
    -0.70
    *)
    -0.70
     john
    -0.69
    POSITIVE LOGITS
    leans
    1.13
    nery
    1.08
    nam
    1.07
    chard
    1.05
    chid
    0.97
    vous
    0.92
    ific
    0.90
    phans
    0.85
    phan
    0.81
    gin
    0.78
    Activations Density 0.790%

    No Known Activations