© 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. 5864
    Prev
    Next
    INDEX
    Explanations

    negative events or outcomes

    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
    288
    +0.14
    0.6%
    441
    +0.13
    0.5%
    151
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    151
    +0.14
    0.16
    288
    +0.13
    0.17
    34
    +0.11
    0.09
    Negative Logits
    alde
    -0.80
    ju
    -0.78
    area
    -0.75
    Origin
    -0.74
    orthy
    -0.71
     Sed
    -0.71
    origin
    -0.71
    oak
    -0.68
    ogly
    -0.67
    llers
    -0.67
    POSITIVE LOGITS
    luster
    1.00
     miser
    1.00
     disappoint
    0.72
     Wasserman
    0.71
     Schr
    0.71
    ufact
    0.70
     Downs
    0.70
     failures
    0.69
    hooting
    0.69
    etsk
    0.69
    Activations Density 3.516%

    No Known Activations