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

    Neuronpedia

    Jacobian LensNEW
    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. 12558
    Prev
    Next
    INDEX
    Explanations

    dialogue and description of interactions between characters within stories

    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
    360
    +0.16
    0.5%
    418
    +0.15
    0.5%
    104
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    55
    +0.16
    0.05
    566
    +0.15
    0.04
    360
    +0.14
    0.05
    Negative Logits
    plug
    -1.03
    igr
    -1.01
     Skydragon
    -1.00
    ples
    -1.00
    ĵĺ
    -0.97
    inav
    -0.92
    factor
    -0.92
    bee
    -0.92
    skirts
    -0.91
    etheless
    -0.90
    POSITIVE LOGITS
     Cel
    0.93
     Fed
    0.90
     Dana
    0.89
     Cla
    0.89
     Vec
    0.88
     Conce
    0.88
     Alive
    0.86
     Fein
    0.85
     Qualcomm
    0.85
     Pub
    0.84
    Activations Density 0.611%

    No Known Activations