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. 7-RES-JB
    6. 15006
    Prev
    Next
    INDEX
    Explanations

    political discussions and references

    oai_token-act-pair · gpt-3.5-turbo

    references related to statements or quotes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "!
    -0.98
    !",
    -0.94
    !".
    -0.88
    ").
    -0.84
    .",
    -0.83
    ",
    -0.83
    ".
    -0.78
    "),
    -0.78
    ".[
    -0.76
    "))
    -0.75
    POSITIVE LOGITS
     Congressman
    0.88
    Secretary
    0.87
     GOODMAN
    0.83
     NPR
    0.82
     Secretary
    0.79
    govtrack
    0.73
     PRESIDENT
    0.73
    Senator
    0.73
     Senator
    0.71
    glas
    0.71
    Activations Density 0.451%

    No Known Activations