© 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. 12925
    Prev
    Next
    INDEX
    Explanations

    quotes in text

    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
    640
    +0.16
    0.6%
    48
    +0.14
    0.5%
    418
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    108
    +0.16
    0.07
    426
    +0.14
    0.06
    240
    +0.13
    0.05
    Negative Logits
     repro
    -0.80
     answ
    -0.79
     rall
    -0.79
     toss
    -0.78
     filib
    -0.77
     reprint
    -0.76
     disagree
    -0.76
    oho
    -0.76
     appro
    -0.75
     Glas
    -0.75
    POSITIVE LOGITS
    Everything
    1.27
    We
    1.26
    Our
    1.25
    What
    1.25
    Operation
    1.20
    Mand
    1.18
    Excellent
    1.16
    I
    1.15
    Behind
    1.15
    You
    1.15
    Activations Density 0.144%

    No Known Activations