© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 19663
    Prev
    Next
    INDEX
    Explanations

    mentions of human anatomy, specifically brains and heads

    oai_token-act-pair · gpt-3.5-turbo

    references to the brain and mental processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Prosecut
    -0.65
    ression
    -0.64
    ECH
    -0.62
    INA
    -0.62
    ressive
    -0.61
    ee
    -0.61
    card
    -0.61
    rav
    -0.61
    onomy
    -0.60
    Delivery
    -0.60
    POSITIVE LOGITS
    chool
    1.54
    mith
    1.45
    paces
    1.41
    pring
    1.38
    pace
    1.33
    creen
    1.32
    cale
    1.30
    ystem
    1.27
    hips
    1.25
    hare
    1.19
    Activations Density 0.088%

    No Known Activations