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. 1787
    Prev
    Next
    INDEX
    Explanations

    high-level political figures and their actions or affiliations

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals and their actions or roles over time

    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
     tomorrow
    -0.95
     tonight
    -0.78
    icago
    -0.70
     yesterday
    -0.68
     Consent
    -0.65
    oda
    -0.65
    aucus
    -0.64
    later
    -0.62
    nesday
    -0.62
     FY
    -0.62
    POSITIVE LOGITS
     steadily
    1.13
     accumulated
    1.02
     amassed
    0.93
     progressively
    0.90
     racked
    0.87
     tirelessly
    0.87
     continuously
    0.87
     progressed
    0.86
     relentlessly
    0.85
     gradually
    0.85
    Activations Density 0.202%

    No Known Activations