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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 8-RES-JB
    6. 2891
    Prev
    Next
    INDEX
    Explanations

    names of political figures

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals holding the title of "Senator."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Zimbabwe
    -0.78
     Gamb
    -0.66
     Georgian
    -0.65
     Royale
    -0.65
    boy
    -0.65
    maker
    -0.64
     Carnegie
    -0.64
     Springer
    -0.64
     Maker
    -0.63
     Starr
    -0.61
    POSITIVE LOGITS
    itivity
    1.40
    itives
    1.18
    itive
    1.15
    ibly
    1.08
    atile
    1.07
    ĸļ
    1.02
    ational
    1.02
    ibility
    1.02
    itiveness
    1.01
    ationally
    1.01
    Activations Density 0.030%

    No Known Activations