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. 8-RES-JB
    6. 18323
    Prev
    Next
    INDEX
    Explanations

    terms related to legal or investigative activities

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to emergency situations and legal contexts

    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
    âĢķ
    -0.81
     â̦"
    -0.77
     ______
    -0.76
    .",
    -0.73
    â̦"
    -0.71
    ––
    -0.68
     ..."
    -0.68
    ...)
    -0.67
     WHEN
    -0.67
    ..."
    -0.66
    POSITIVE LOGITS
    ogether
    1.02
     analysts
    0.89
     observers
    0.88
     spokeswoman
    0.88
     spokesman
    0.88
    izens
    0.86
    goers
    0.86
     campaigners
    0.83
    inarily
    0.83
    ologists
    0.82
    Activations Density 0.387%

    No Known Activations