© 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. 10816
    Prev
    Next
    INDEX
    Explanations

    downloads and podcasts

    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
    530
    +0.08
    0.6%
    689
    +0.07
    0.5%
    688
    +0.06
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    553
    +0.08
    0.02
    723
    +0.07
    0.02
    701
    +0.06
    0.01
    Negative Logits
    wcs
    -0.49
    rained
    -0.46
    owered
    -0.46
    antry
    -0.45
     pains
    -0.45
    cn
    -0.43
     enthusi
    -0.42
     mas
    -0.42
    uria
    -0.42
    ukemia
    -0.41
    POSITIVE LOGITS
     Upper
    0.46
     Exile
    0.45
    FTWARE
    0.45
    tails
    0.45
    papers
    0.44
     Faces
    0.43
     DF
    0.43
     Estonia
    0.42
     Bund
    0.40
     Ko
    0.40
    Activations Density 0.087%

    No Known Activations