© 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. 3-RES-JB
    11. 15229
    Prev
    Next
    INDEX
    Explanations

    instances where the term "bit" is used in a figurative sense

    oai_token-act-pair · gpt-3.5-turbo

    expressions indicating a small or moderate degree of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inarily
    -0.78
    ovies
    -0.75
    doms
    -0.73
    aden
    -0.69
    ities
    -0.68
    endars
    -0.66
     Siber
    -0.65
    stice
    -0.65
    ateful
    -0.65
    irie
    -0.65
    POSITIVE LOGITS
     bit
    0.87
    terness
    0.82
    umen
    0.80
     prick
    0.68
    buck
    0.66
    plug
    0.66
     BIT
    0.65
     aspirin
    0.65
    umin
    0.65
    meal
    0.65
    Activations Density 0.019%

    No Known Activations