© 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. 9-RES-JB
    11. 15380
    Prev
    Next
    INDEX
    Explanations

    references to or mentions of men and related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to men and their presence in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IVERS
    -0.84
    VICE
    -0.73
    REDACTED
    -0.69
    Closure
    -0.65
    Main
    -0.64
    Berry
    -0.63
    worthiness
    -0.63
    âĺħâĺħ
    -0.61
    KEN
    -0.60
    DATA
    -0.59
    POSITIVE LOGITS
    opausal
    1.45
    endez
    1.29
    volent
    1.27
    aced
    1.19
    orah
    1.19
    ager
    1.19
    aces
    1.17
    stru
    1.04
    folk
    1.00
    uscript
    0.99
    Activations Density 0.080%

    No Known Activations