© 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. 3135
    Prev
    Next
    INDEX
    Explanations

    terms related to monotony or tediousness

    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
    658
    +0.08
    0.5%
    515
    +0.07
    0.4%
    404
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.08
    0.05
    151
    +0.07
    0.05
    613
    +0.07
    0.03
    Negative Logits
    WOR
    -0.63
    spin
    -0.60
    GER
    -0.58
    Journal
    -0.57
    don
    -0.56
    WT
    -0.53
    words
    -0.52
     OPS
    -0.52
    lands
    -0.51
    faced
    -0.51
    POSITIVE LOGITS
    icity
    0.94
    itri
    0.74
    ices
    0.74
    ics
    0.72
    ically
    0.72
     unden
    0.62
    Īè
    0.62
    ople
    0.62
    ause
    0.61
    iolet
    0.60
    Activations Density 0.347%

    No Known Activations