Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 9848
    Prev
    Next
    INDEX
    Explanations

    references to men or males in the text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "men" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Accessory
    -0.82
    Assembly
    -0.78
    EV
    -0.75
    Deal
    -0.74
    REDACTED
    -0.70
    Front
    -0.69
    Fuel
    -0.68
    KEN
    -0.68
    Commercial
    -0.68
    Capital
    -0.68
    POSITIVE LOGITS
    opausal
    1.21
    uscript
    1.15
    endez
    1.12
    ager
    1.11
    volent
    1.08
    folk
    0.97
     oun
    0.95
    orah
    0.95
    iscal
    0.91
     ejac
    0.89
    Activations Density 0.042%

    No Known Activations