© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 20327
    Prev
    Next
    INDEX
    Explanations

    phrases related to oceanography and atmospheric science

    oai_token-act-pair · gpt-3.5-turbo

    references to scientific organizations and research-related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    raped
    -0.79
    idious
    -0.68
    ween
    -0.67
     wedge
    -0.65
    ardless
    -0.65
    gro
    -0.64
    flame
    -0.64
    love
    -0.63
     emot
    -0.63
    hole
    -0.62
    POSITIVE LOGITS
     Association
    1.00
     Sciences
    0.85
     Society
    0.84
     Laboratory
    0.83
     Survey
    0.82
     Observatory
    0.81
     Institute
    0.81
    onnaissance
    0.80
     Fisheries
    0.80
     Federation
    0.80
    Activations Density 0.096%

    No Known Activations