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. 11-RES-JB
    6. 24268
    Prev
    Next
    INDEX
    Explanations

    references to male individuals as a subject of discussion

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual

    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
    •Male Descriptors

    No Comments

    Negative Logits
     antioxid
    -0.61
     pregn
    -0.59
     Gems
    -0.59
     Veter
    -0.59
     Dominion
    -0.59
     Mandatory
    -0.58
     Definitions
    -0.57
     Reading
    -0.56
     Curious
    -0.56
     Header
    -0.56
    POSITIVE LOGITS
    zbollah
    1.38
    'd
    1.30
    aped
    1.21
    resy
    1.20
    ading
    1.14
    eded
    1.11
    uristic
    1.08
     was
    1.07
    aded
    1.06
    reditary
    1.04
    Activations Density 0.299%

    No Known Activations