Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 20126
    Prev
    Next
    INDEX
    Explanations

    dates in the format "Month Day, Year" and numbers related to dates

    oai_token-act-pair · gpt-3.5-turbo

    references to specific dates and periods

    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
    ------------------------
    -0.97
     thous
    -0.92
    hap
    -0.82
     Greenberg
    -0.78
     Sherman
    -0.78
     Moss
    -0.78
    Magn
    -0.77
     Gutenberg
    -0.77
    EF
    -0.75
     Hag
    -0.75
    POSITIVE LOGITS
     2016
    1.36
    2016
    1.29
    16
    1.10
     16
    1.05
     1916
    0.92
     86
    0.82
     166
    0.80
    166
    0.79
     1986
    0.77
    idian
    0.76
    Activations Density 0.235%

    No Known Activations