© 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. 10297
    Prev
    Next
    INDEX
    Explanations

    words related to requesting, guessing, and naming

    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
    1
    +0.09
    0.4%
    493
    +0.08
    0.4%
    77
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    70
    +0.09
    0.03
    131
    +0.08
    0.02
    373
    +0.08
    -0.01
    Negative Logits
    ensions
    -0.76
    isoft
    -0.73
    auld
    -0.71
    ================================
    -0.67
    akura
    -0.66
    Tomorrow
    -0.65
    INAL
    -0.65
    WAR
    -0.64
    kefeller
    -0.64
    idel
    -0.64
    POSITIVE LOGITS
    lihood
    0.64
     Garfield
    0.62
     Cricket
    0.57
     MN
    0.55
     domain
    0.55
     liar
    0.55
     fraction
    0.55
     bud
    0.55
     KM
    0.54
     Twain
    0.53
    Activations Density 0.089%

    No Known Activations