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

    Neuronpedia

    APICircuit 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. 20001
    Prev
    Next
    INDEX
    Explanations

    dates in the format month-day with a high activation value

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of specific formatting or structure, such as timestamps or placeholders in a document

    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
     eleph
    -1.21
     pione
    -1.16
     practition
    -1.15
    Þ
    -1.15
    aditional
    -1.14
    ò
    -1.11
    ThumbnailImage
    -1.10
    Ý
    -1.06
     externalTo
    -1.05
    ě
    -1.05
    POSITIVE LOGITS
    ,
    1.08
    ,...
    0.86
    ,-
    0.85
    ,.
    0.74
    ,,
    0.70
    .,
    0.67
    ,,,,,,,,
    0.64
    Merit
    0.63
    %,
    0.62
    ,)
    0.62
    Activations Density 0.056%

    No Known Activations