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. 11082
    Prev
    Next
    INDEX
    Explanations

    questions starting with "So what"

    oai_token-act-pair · gpt-3.5-turbo

    questions that begin with "what."

    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
    renheit
    -0.75
    ãĥĭ
    -0.65
    anus
    -0.65
    rim
    -0.64
    agonists
    -0.64
    20439
    -0.63
    gression
    -0.62
    mens
    -0.62
    apsed
    -0.61
    cit
    -0.61
    POSITIVE LOGITS
     exactly
    1.15
     does
    0.96
    ?
    0.94
     do
    0.92
    ?????
    0.90
     happens
    0.90
     SHOULD
    0.89
     DOES
    0.86
    ?!
    0.85
    !?
    0.85
    Activations Density 0.083%

    No Known Activations