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

    Neuronpedia

    APICircuit 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. 10-RES-JB
    6. 17895
    Prev
    Next
    INDEX
    Explanations

    mentions of reports and the organization "Center for American Progress."

    oai_token-act-pair · gpt-3.5-turbo

    statements or reports regarding societal issues faced by specific marginalized communities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Frieza
    -0.84
     manoeuv
    -0.78
     centrif
    -0.75
     electrons
    -0.75
     upgr
    -0.74
     Saiyan
    -0.73
     orbital
    -0.73
    ocular
    -0.73
    XT
    -0.72
     gamb
    -0.72
    POSITIVE LOGITS
     Transgender
    1.30
     Homeless
    1.21
     LGBTQ
    1.21
     Feminist
    1.18
     Amnesty
    1.18
     ACLU
    1.16
     advocacy
    1.13
     Disability
    1.13
    LGBT
    1.11
     Families
    1.10
    Activations Density 0.783%

    No Known Activations