© 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. 2507
    Prev
    Next
    INDEX
    Explanations

    phrases related to author attributions at the beginning of a text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter "L" in various contexts

    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
     limits
    -0.63
     democracies
    -0.61
     tailor
    -0.61
     Mobil
    -0.59
     juggling
    -0.56
     lies
    -0.56
     jails
    -0.55
     avail
    -0.54
     exceptions
    -0.53
     Shelter
    -0.53
    POSITIVE LOGITS
    ledged
    1.39
    oided
    1.31
    didn
    1.31
    lished
    1.28
    sed
    1.27
    ved
    1.27
    emed
    1.27
    wrote
    1.26
    overed
    1.26
    aughed
    1.25
    Activations Density 0.310%

    No Known Activations