© 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. 19327
    Prev
    Next
    INDEX
    Explanations

    dates (specific month and year combinations)

    oai_token-act-pair · gpt-3.5-turbo

    important numerical and temporal references in the text

    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
    "},"
    -0.62
    sbm
    -0.60
    channelAvailability
    -0.59
    arthed
    -0.58
    icators
    -0.55
    inventoryQuantity
    -0.54
     viz
    -0.54
    english
    -0.52
    \":
    -0.51
    ãĥİ
    -0.49
    POSITIVE LOGITS
    ,
    1.40
    ,...
    1.13
    ,-
    1.01
    .,
    0.93
    ,.
    0.93
    ,,
    0.92
    âĢ¢âĢ¢
    0.71
    ,[
    0.69
    !,
    0.68
    ,—
    0.66
    Activations Density 0.552%

    No Known Activations