© 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. 7045
    Prev
    Next
    INDEX
    Explanations

    opinions or beliefs expressed by individuals

    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
    638
    +0.16
    0.6%
    713
    +0.13
    0.5%
    20
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    713
    +0.16
    0.07
    638
    +0.13
    0.07
    431
    +0.11
    0.07
    Negative Logits
     casualty
    -0.70
    jury
    -0.70
     pend
    -0.69
     Stephenson
    -0.68
    osi
    -0.67
    iop
    -0.66
    conn
    -0.65
     Metatron
    -0.64
     Ez
    -0.63
    visors
    -0.62
    POSITIVE LOGITS
    SPONSORED
    0.90
     happening
    0.87
     entails
    0.79
    Ca
    0.77
     termed
    0.74
     boils
    0.74
    ESA
    0.73
    BILL
    0.73
    ulse
    0.72
    UFC
    0.71
    Activations Density 1.584%

    No Known Activations