© 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. 13694
    Prev
    Next
    INDEX
    Explanations

    mentions of medical conditions or disorders, specifically focusing on schizophrenia

    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
    545
    +0.02
    0.5%
    195
    +0.02
    0.4%
    550
    +0.02
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    578
    +0.02
    0.06
    114
    +0.02
    0.07
    450
    +0.02
    0.06
    Negative Logits
    phies
    -0.17
    ga
    -0.16
    cule
    -0.16
    poons
    -0.16
     dirt
    -0.15
     snipp
    -0.15
    gre
    -0.15
    isted
    -0.14
    gs
    -0.14
    cock
    -0.14
    POSITIVE LOGITS
     schizophren
    0.26
     schizophrenia
    0.24
     psychosis
    0.18
    izophren
    0.17
     Spectrum
    0.17
     ide
    0.16
     psychotic
    0.15
     spectrum
    0.15
     delusions
    0.15
    ational
    0.15
    Activations Density 9.653%

    No Known Activations