© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 39897
    Prev
    Next
    INDEX
    Explanations

    medical terms and information related to health care 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
    447
    +0.14
    0.7%
    519
    +0.10
    0.5%
    235
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    508
    +0.14
    0.11
    235
    +0.10
    0.13
    150
    +0.09
    0.05
    Negative Logits
     Strongh
    -0.75
    urat
    -0.73
     iPod
    -0.71
     Stronghold
    -0.69
    ontent
    -0.68
     Territories
    -0.66
    ilogy
    -0.64
    pload
    -0.63
    peat
    -0.62
     DRM
    -0.62
    POSITIVE LOGITS
     practitioner
    1.14
     physicians
    1.03
     physician
    1.01
     patients
    1.00
     Patient
    0.97
    iatrics
    0.96
     doctors
    0.96
     diagnoses
    0.95
     doctor
    0.95
     Clin
    0.93
    Activations Density 18.872%

    No Known Activations