© 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. 7720
    Prev
    Next
    INDEX
    Explanations

    the word "scoop"

    oai_token-act-pair · gpt-3.5-turbo

    references to measuring or collecting quantities, specifically using "scoop" and "sprint."

    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
    Downloadha
    -0.74
    idad
    -0.74
    ior
    -0.70
    rh
    -0.69
    wealth
    -0.68
    aders
    -0.68
    amacare
    -0.67
    forcement
    -0.66
    cit
    -0.65
    hart
    -0.65
    POSITIVE LOGITS
    ing
    1.40
    ed
    1.11
    edly
    0.93
    hest
    0.85
    eering
    0.84
    raction
    0.77
    ledge
    0.76
    sie
    0.75
    angular
    0.75
    ingham
    0.72
    Activations Density 0.084%

    No Known Activations