Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 6171
    Prev
    Next
    INDEX
    Explanations

    medical research-related terms and procedures

    oai_token-act-pair · gpt-3.5-turbo

    elements related to statistical analysis and medical research data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atron
    -0.76
    atche
    -0.73
    Jet
    -0.68
     launches
    -0.67
     Centauri
    -0.67
     goodbye
    -0.65
    Throw
    -0.64
    achev
    -0.64
    ulence
    -0.64
     exile
    -0.63
    POSITIVE LOGITS
     questionnaire
    1.06
    ivariate
    0.99
     placebo
    0.97
     statistically
    0.97
     covari
    0.96
    icter
    0.93
     preval
    0.93
     clinically
    0.92
     demographic
    0.91
     psychiat
    0.91
    Activations Density 1.137%

    No Known Activations