© 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. 3516
    Prev
    Next
    INDEX
    Explanations

    news articles and reports related to featured individuals and events

    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
    70
    +0.14
    0.5%
    634
    +0.14
    0.5%
    160
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    632
    +0.14
    0.03
    241
    +0.14
    0.03
    114
    +0.13
    0.03
    Negative Logits
     assum
    -0.97
    isd
    -0.96
     spam
    -0.92
    kb
    -0.90
    iod
    -0.89
     advoc
    -0.89
    qs
    -0.89
    fee
    -0.87
    pecially
    -0.86
     challeng
    -0.85
    POSITIVE LOGITS
     Gleaming
    1.09
     Opinion
    1.05
     Retrieved
    1.01
     Approximately
    1.00
     Ahead
    0.98
     Reached
    0.96
     WATCHED
    0.95
     Views
    0.95
     Sources
    0.95
     GOODMAN
    0.94
    Activations Density 0.210%

    No Known Activations