© 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. 10209
    Prev
    Next
    INDEX
    Explanations

    keywords or phrases that are important or central to a topic

    oai_token-act-pair · gpt-3.5-turbo

    the word "key" and its variations, indicating important elements or concepts 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
    ©¶æ
    -0.79
    uthor
    -0.70
    agle
    -0.69
     Leone
    -0.66
    uum
    -0.66
    ateur
    -0.63
    ormal
    -0.63
    Ń·
    -0.62
    asionally
    -0.62
     Brig
    -0.62
    POSITIVE LOGITS
    stone
    1.43
    notes
    1.19
    stones
    1.18
    stroke
    1.17
    stro
    1.15
    hole
    1.10
    frame
    1.02
     ingredient
    1.01
    fram
    1.01
    binding
    0.98
    Activations Density 0.042%

    No Known Activations