© 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. 3388
    Prev
    Next
    INDEX
    Explanations

    references to group interactions or actions

    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
    +0.35
    1.3%
    587
    +0.14
    0.5%
    561
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    561
    +0.35
    0.09
    97
    +0.14
    0.07
    469
    +0.14
    0.07
    Negative Logits
    ashtra
    -0.91
     fert
    -0.87
    acus
    -0.87
    hyde
    -0.86
     prescribe
    -0.82
    resy
    -0.80
    henko
    -0.79
    hra
    -0.79
    ctuary
    -0.77
    atorium
    -0.77
    POSITIVE LOGITS
     sorts
    1.39
     disparate
    0.89
     events
    0.80
     goodies
    0.79
    Topics
    0.79
     eight
    0.79
     twelve
    0.78
     assorted
    0.77
     overlapping
    0.77
     posts
    0.77
    Activations Density 1.616%

    No Known Activations