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. 9-RES-JB
    6. 15079
    Prev
    Next
    INDEX
    Explanations

    names of committees, government bodies, or legal proceedings

    oai_token-act-pair · gpt-3.5-turbo

    instances related to appearances before legal or governmental entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    venant
    -0.78
    accompan
    -0.74
    opsis
    -0.66
    çīĪ
    -0.63
     complication
    -0.62
    ettel
    -0.62
    Vers
    -0.61
    itars
    -0.61
    ource
    -0.59
    etting
    -0.59
    POSITIVE LOGITS
     Congress
    1.24
     parliament
    1.13
     lawmakers
    1.12
     congress
    1.08
     Parliament
    1.07
     legislators
    1.05
     Subcommittee
    0.99
     jurors
    0.94
     Commissioners
    0.94
     commissioners
    0.94
    Activations Density 0.070%

    No Known Activations