© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 40323
    Prev
    Next
    INDEX
    Explanations

    medical and health-related terms, including diagnoses, physicians, clinical details, health assessments, diseases, medications, and 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
    644
    +0.13
    0.6%
    355
    +0.11
    0.5%
    328
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.35
    575
    +0.11
    0.20
    326
    +0.10
    0.30
    Negative Logits
    */(
    -0.81
     Vaj
    -0.75
     Dot
    -0.69
     Christensen
    -0.65
     Judges
    -0.65
     newsp
    -0.62
     lever
    -0.62
     peaks
    -0.61
    Jr
    -0.61
    doms
    -0.61
    POSITIVE LOGITS
    aceutical
    0.88
    uana
    0.84
    ysis
    0.80
    Medical
    0.80
    ocaust
    0.78
    xon
    0.77
     cure
    0.76
     ashore
    0.76
    Food
    0.76
    hazard
    0.75
    Activations Density 16.808%

    No Known Activations