© 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. 10145
    Prev
    Next
    INDEX
    Explanations

    instances of the word "man" with a high level of activation

    oai_token-act-pair · gpt-3.5-turbo

    references to "man" and related reports of human actions or incidents

    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
    tnc
    -0.83
     Supplement
    -0.70
     VIDEOS
    -0.66
    inventoryQuantity
    -0.65
    Import
    -0.65
     Destination
    -0.64
    DERR
    -0.63
    Revolution
    -0.62
    âĺħâĺħ
    -0.62
    allery
    -0.61
    POSITIVE LOGITS
    hunt
    1.79
    gling
    1.12
    hole
    1.11
    nered
    1.09
    hood
    1.07
    hattan
    1.03
     surn
    1.00
    ger
    1.00
    volent
    0.99
    handled
    0.98
    Activations Density 0.074%

    No Known Activations