© 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. 2-RES-JB
    11. 18231
    Prev
    Next
    INDEX
    Explanations

    sentences ending in a specific punctuation mark

    oai_token-act-pair · gpt-3.5-turbo

    sentences that conclude with a period

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     metic
    -0.74
     mosqu
    -0.73
    uly
    -0.72
     tyr
    -0.70
    ikuman
    -0.69
    loo
    -0.68
     purse
    -0.66
     footing
    -0.65
     defe
    -0.65
     challeng
    -0.64
    POSITIVE LOGITS
     However
    1.09
     Additionally
    1.08
     Unfortunately
    1.01
     Likewise
    1.01
     Therefore
    1.01
     Similarly
    1.00
     Moreover
    1.00
     They
    1.00
     Furthermore
    0.99
     Flavoring
    0.97
    Activations Density 1.666%

    No Known Activations