© 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. 10437
    Prev
    Next
    INDEX
    Explanations

    dates or time-related numerical sequences

    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
    393
    +0.25
    0.8%
    699
    +0.22
    0.7%
    725
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.25
    0.07
    393
    +0.22
    0.08
    306
    +0.14
    0.06
    Negative Logits
    lime
    -1.00
    Led
    -0.93
    Īè
    -0.93
    erers
    -0.92
     Folder
    -0.90
    Exec
    -0.89
    Syn
    -0.89
    è¦
    -0.88
    ÙĴ
    -0.87
    BILITIES
    -0.85
    POSITIVE LOGITS
     latter
    1.22
     1970
    1.15
     inception
    1.15
     crash
    1.10
     1960
    1.06
     dawn
    1.04
     ages
    1.04
     1990
    1.03
     advent
    1.01
     late
    1.01
    Activations Density 1.073%

    No Known Activations