© 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 Local
    9. 6-RES_SCL-AJT
    11. 31344
    Prev
    Next
    INDEX
    Explanations

    texts referencing individuals, historical events, and locations without any common theme

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    447
    +0.23
    0.9%
    575
    +0.13
    0.5%
    365
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.23
    0.30
    352
    +0.13
    0.29
    154
    +0.12
    0.29
    Negative Logits
     sidx
    -0.80
     unmarked
    -0.79
     reception
    -0.78
     Bunny
    -0.77
     Roc
    -0.75
     spiral
    -0.70
    creen
    -0.70
    lder
    -0.69
     Somerset
    -0.69
     buggy
    -0.69
    POSITIVE LOGITS
    ¬
    0.97
    orsi
    0.93
    âĹ¼
    0.93
    º
    0.91
    loop
    0.91
    âĢł
    0.90
    los
    0.85
    drivers
    0.85
    dayName
    0.85
    lr
    0.83
    Activations Density 9.836%

    No Known Activations