© 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. 7-RES-JB
    11. 16332
    Prev
    Next
    INDEX
    Explanations

    references to previous or past studies, research, surveys, or operations

    oai_token-act-pair · gpt-3.5-turbo

    references to previous studies and research findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sung
    -0.69
    Pri
    -0.64
    $$$$
    -0.62
     ILCS
    -0.60
    onics
    -0.58
    ãĤª
    -0.57
     Appropri
    -0.57
    Station
    -0.57
    ueller
    -0.56
    ioxide
    -0.55
    POSITIVE LOGITS
     administrations
    0.74
    bernatorial
    0.73
     generations
    0.72
     installments
    0.71
    iations
    0.70
     iterations
    0.67
    inctions
    0.65
    quit
    0.64
     eras
    0.63
     unsuccessfully
    0.62
    Activations Density 0.242%

    No Known Activations