© 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. 10214
    Prev
    Next
    INDEX
    Explanations

    phrases related to solving puzzles, especially in the context of videogames and cognitive challenges

    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
    326
    +0.18
    0.8%
    679
    +0.14
    0.6%
    491
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.18
    0.08
    288
    +0.14
    0.09
    151
    +0.14
    0.07
    Negative Logits
    rol
    -0.77
    redits
    -0.76
     gluc
    -0.75
    glomer
    -0.74
    ulf
    -0.73
    riott
    -0.72
    lav
    -0.72
    enses
    -0.71
    rolog
    -0.71
    ributes
    -0.70
    POSITIVE LOGITS
    uzzle
    1.05
     puzzles
    0.98
    ĸļ
    0.96
     Shack
    0.88
     solving
    0.87
     puzzle
    0.87
    igsaw
    0.80
     scramble
    0.80
    hooting
    0.79
     Puzz
    0.78
    Activations Density 1.000%

    No Known Activations