© 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. 11-RES-JB
    11. 18776
    Prev
    Next
    INDEX
    Explanations

    numerical information (such as counts, quantities, or rankings)

    oai_token-act-pair · gpt-3.5-turbo

    quantitative references indicating frequency or quantity of events and items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icz
    -0.69
    uncture
    -0.69
    ãĥ¼ãĥ
    -0.67
    lement
    -0.62
    ategory
    -0.59
    variable
    -0.58
    ocol
    -0.57
    Movie
    -0.57
    SpaceEngineers
    -0.56
    Spoiler
    -0.56
    POSITIVE LOGITS
     apiece
    1.04
     involving
    0.95
     since
    0.95
     besides
    0.94
     totaling
    0.89
     ones
    0.89
     others
    0.88
     in
    0.88
     before
    0.88
    .:
    0.83
    Activations Density 0.240%

    No Known Activations