© 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. 33117
    Prev
    Next
    INDEX
    Explanations

    mentions of medical conditions or diseases and potential cures or treatments for them

    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
    10
    +0.15
    0.7%
    447
    +0.14
    0.6%
    642
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.27
    326
    +0.14
    0.23
    10
    +0.11
    0.10
    Negative Logits
    ible
    -0.87
    ibly
    -0.82
    shaw
    -0.79
    adesh
    -0.74
    ives
    -0.73
    ifts
    -0.72
    iblings
    -0.70
    IGHTS
    -0.70
    avier
    -0.70
    herty
    -0.70
    POSITIVE LOGITS
    eers
    0.76
     abroad
    0.74
    rers
    0.71
     Emanuel
    0.64
     outbreak
    0.64
    nces
    0.63
    eer
    0.63
     quarantine
    0.62
     leukemia
    0.62
     Ebola
    0.62
    Activations Density 8.939%

    No Known Activations