© 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. 6891
    Prev
    Next
    INDEX
    Explanations

    adjectives indicating size or importance

    oai_token-act-pair · gpt-3.5-turbo

    phrases or expressions that emphasize the significance of an event or concept, particularly those described as "big."

    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
    apons
    -0.78
    Reviewed
    -0.77
     Emin
    -0.75
    ptives
    -0.74
    forms
    -0.73
    atography
    -0.69
     Seym
    -0.68
    manship
    -0.67
    AUT
    -0.67
    opes
    -0.67
    POSITIVE LOGITS
    gie
    1.24
     chunk
    1.13
    oted
    1.12
     ol
    1.04
     deal
    1.02
    gest
    0.96
     swath
    0.95
     difference
    0.87
    GER
    0.85
     misconception
    0.84
    Activations Density 0.069%

    No Known Activations