© 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 EvalsExportsinterp-engineNEWAPI 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. 11851
    Prev
    Next
    INDEX
    Explanations

    critical remarks or negative evaluations

    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
    608
    +0.12
    0.5%
    490
    +0.11
    0.5%
    718
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.12
    0.16
    718
    +0.11
    0.18
    608
    +0.10
    0.20
    Negative Logits
    cember
    -0.78
     Practices
    -0.77
    ?".
    -0.77
    hammad
    -0.74
    assic
    -0.70
     ÃĹ
    -0.69
    omm
    -0.68
     Picture
    -0.68
    scribe
    -0.67
    代
    -0.67
    POSITIVE LOGITS
     disappoint
    0.88
     dissu
    0.86
     grim
    0.84
     relent
    0.83
     surpr
    0.81
     deter
    0.80
     surprises
    0.80
     unsurprisingly
    0.80
     dismay
    0.79
     surprising
    0.79
    Activations Density 7.306%

    No Known Activations