© 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
    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. 1619
    Prev
    Next
    INDEX
    Explanations

    dialogue within a story, including character interactions and exchanges

    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
    640
    +0.23
    0.8%
    393
    +0.17
    0.6%
    48
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    108
    +0.23
    0.05
    426
    +0.17
    0.04
    627
    +0.12
    0.03
    Negative Logits
     scra
    -1.00
     mapping
    -0.98
     streaming
    -0.97
     frontline
    -0.95
     flooded
    -0.94
     sprint
    -0.94
     transitioning
    -0.93
     transgender
    -0.93
     aging
    -0.92
     overshadow
    -0.92
    POSITIVE LOGITS
    Excellent
    1.53
    True
    1.51
    Very
    1.46
    Really
    1.45
    Never
    1.45
    Better
    1.42
    What
    1.41
    Enough
    1.41
    Mand
    1.41
    Tell
    1.41
    Activations Density 0.179%

    No Known Activations