© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 8967
    Prev
    Next
    INDEX
    Explanations

    questions within the 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
    Neuron Alignment
    Index
    Value
    % of L₁
    393
    +0.22
    0.7%
    55
    +0.19
    0.6%
    638
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    55
    +0.22
    0.10
    14
    +0.19
    0.05
    102
    +0.15
    0.06
    Negative Logits
    heres
    -1.12
    hyde
    -1.07
    hedon
    -1.03
    bilt
    -1.00
    itches
    -0.98
    hens
    -0.97
    lems
    -0.92
    tails
    -0.90
    gypt
    -0.88
    opez
    -0.86
    POSITIVE LOGITS
     happening
    1.26
     meant
    1.12
     supposed
    1.09
    nt
    1.07
     actually
    1.02
    omorphic
    0.99
     implied
    0.97
     transpired
    0.96
     really
    0.94
    kus
    0.93
    Activations Density 0.885%

    No Known Activations