© 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 EvalsExportsinterp-engineNEWAPI 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. 35765
    Prev
    Next
    INDEX
    Explanations

    percentage values mentioned in the text

    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
    +0.16
    0.7%
    147
    +0.11
    0.5%
    173
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    456
    +0.16
    0.06
    661
    +0.11
    0.05
    745
    +0.10
    -0.06
    Negative Logits
     compr
    -0.76
    zek
    -0.67
     compan
    -0.67
    itiz
    -0.66
    elf
    -0.65
    ãĤ©
    -0.65
     detrim
    -0.61
     dign
    -0.61
     contrace
    -0.61
     scrambled
    -0.61
    POSITIVE LOGITS
     ABV
    0.92
    +.
    0.91
    +)
    0.86
    +,
    0.82
    bps
    0.76
    +
    0.73
    Percent
    0.73
     opacity
    0.71
     throttle
    0.71
     apiece
    0.70
    Activations Density 4.766%

    No Known Activations