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. 0-RES-JB
    6. 20878
    Prev
    Next
    INDEX
    Explanations

    proposals related to government policies or legislative actions

    oai_token-act-pair · gpt-3.5-turbo

    references to policy proposals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    astery
    -0.72
     healer
    -0.66
     Veter
    -0.65
     Lash
    -0.64
    pped
    -0.62
    fi
    -0.60
     followed
    -0.60
     located
    -0.59
    thia
    -0.59
     Unt
    -0.59
    POSITIVE LOGITS
     proposals
    3.55
     proposal
    2.18
     propositions
    1.67
     suggestions
    1.65
     initiatives
    1.62
     plans
    1.61
     recommendations
    1.60
     proposed
    1.58
     ideas
    1.56
     proposes
    1.56
    Activations Density 0.009%

    No Known Activations