© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 11595
    Prev
    Next
    INDEX
    Explanations

    words related to medical diagnosis and symptoms

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    288
    +0.23
    0.7%
    651
    +0.14
    0.5%
    195
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.23
    0.09
    651
    +0.14
    0.05
    540
    +0.14
    0.07
    Negative Logits
    perm
    -1.09
    heed
    -1.00
     actionGroup
    -0.98
    erker
    -0.98
    berman
    -0.98
    atan
    -0.98
    lav
    -0.94
    atility
    -0.93
    yss
    -0.92
    encer
    -0.92
    POSITIVE LOGITS
    ostics
    1.59
    ostic
    1.42
    ptoms
    1.35
    osis
    1.30
    igmatic
    1.14
     Diagn
    1.09
     Symptoms
    1.07
    abetes
    1.06
    Plex
    1.01
     symptoms
    1.00
    Activations Density 0.998%

    No Known Activations