© 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. 7472
    Prev
    Next
    INDEX
    Explanations

    medical conditions or illnesses related to HIV, such as AIDS, cancer, multiple sclerosis, and depression

    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
    +0.16
    0.6%
    359
    +0.14
    0.5%
    146
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.16
    0.11
    444
    +0.14
    0.07
    116
    +0.14
    0.06
    Negative Logits
    Reviewer
    -1.22
     avail
    -0.94
    leon
    -0.93
    vol
    -0.93
    comings
    -0.91
    ellation
    -0.86
    abee
    -0.85
    etary
    -0.83
    compan
    -0.82
    baugh
    -0.80
    POSITIVE LOGITS
     prevention
    1.33
     Prevention
    1.19
     mell
    1.11
     worsened
    1.03
     diagnosis
    1.01
     ridden
    1.01
     stigma
    0.95
     diagnoses
    0.93
     exacerbated
    0.92
     stemming
    0.89
    Activations Density 0.861%

    No Known Activations