© 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. 10-RES-JB
    11. 11005
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the provision or offering of information or advice

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the presentation of advice or suggestions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    azo
    -0.80
    paces
    -0.70
    adra
    -0.65
    pling
    -0.65
     exting
    -0.64
     cumbers
    -0.64
    brance
    -0.64
    psc
    -0.63
    glomer
    -0.63
    osph
    -0.63
    POSITIVE LOGITS
     insights
    1.67
     insight
    1.64
     anecdotes
    1.48
     answers
    1.47
     advice
    1.46
     insightful
    1.40
     thoughts
    1.31
     tips
    1.30
     facts
    1.30
     recommendations
    1.29
    Activations Density 0.387%

    No Known Activations