© 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. 35831
    Prev
    Next
    INDEX
    Explanations

    names of people related to medical conditions

    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
    728
    +0.10
    0.6%
    311
    +0.07
    0.4%
    103
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.10
    0.14
    103
    +0.07
    0.12
    311
    +0.07
    -0.02
    Negative Logits
    kefeller
    -0.64
    plates
    -0.61
    enegger
    -0.60
    staking
    -0.59
    ppa
    -0.59
    fleet
    -0.59
    shots
    -0.57
    senal
    -0.56
    fires
    -0.56
    pling
    -0.56
    POSITIVE LOGITS
    reet
    0.77
    ophe
    0.75
    roph
    0.72
    ruct
    0.72
    reme
    0.69
    rophic
    0.68
    ict
    0.66
    hetics
    0.65
    oly
    0.62
    re
    0.62
    Activations Density 7.670%

    No Known Activations