© 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. 4-RES-JB
    11. 12572
    Prev
    Next
    INDEX
    Explanations

    lists of items or categories in a sentence, potentially related to inventory or shopping lists

    oai_token-act-pair · gpt-3.5-turbo

    commas or punctuation used in lists and categorization

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

    No Comments

    Negative Logits
    herent
    -0.74
    ocese
    -0.73
    ¬¼
    -0.72
    ukong
    -0.71
    lyak
    -0.66
    onym
    -0.65
    abouts
    -0.65
    atsuki
    -0.65
    ocl
    -0.65
    ame
    -0.64
    POSITIVE LOGITS
     etc
    1.17
     albeit
    0.88
    etc
    0.87
     including
    0.80
    sed
    0.79
     which
    0.77
     whereas
    0.72
    while
    0.71
     aka
    0.71
    Magikarp
    0.71
    Activations Density 0.844%

    No Known Activations