© 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. 32167
    Prev
    Next
    INDEX
    Explanations

    specific terms related to a coal mine project and geographically named mines

    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
    +0.13
    0.6%
    525
    +0.13
    0.6%
    549
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.18
    57
    +0.13
    0.07
    541
    +0.13
    0.09
    Negative Logits
    Ö¼
    -0.98
    enegger
    -0.97
    puter
    -0.94
    ROR
    -0.80
    office
    -0.80
    SIGN
    -0.78
    ding
    -0.77
    alities
    -0.74
    ré
    -0.73
    ORD
    -0.73
    POSITIVE LOGITS
     Centauri
    1.41
    cephal
    0.77
    velop
    0.70
     Phi
    0.69
    volent
    0.69
     Quad
    0.69
    qua
    0.68
     rays
    0.67
    imity
    0.66
     essence
    0.66
    Activations Density 5.853%

    No Known Activations