© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 33737
    Prev
    Next
    INDEX
    Explanations

    mentions of specific numbers and quantifiable amounts

    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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.34
    1.6%
    348
    +0.14
    0.7%
    470
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    195
    +0.34
    -0.03
    470
    +0.14
    0.13
    157
    +0.10
    0.21
    Negative Logits
     [âĢ¦]
    -0.75
     whilst
    -0.73
     ().
    -0.67
     civilisation
    -0.63
     independ
    -0.63
     fucking
    -0.63
     ('
    -0.62
    Âł
    -0.61
     ali
    -0.61
    Contents
    -0.60
    POSITIVE LOGITS
     meanwhile
    0.84
     meantime
    0.75
    swers
    0.75
    ibliography
    0.70
     Asked
    0.69
     DeVos
    0.67
     nonprofits
    0.66
     spokeswoman
    0.66
     echoed
    0.64
     aback
    0.63
    Activations Density 27.182%

    No Known Activations