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. 6-RES-JB
    6. 4527
    Prev
    Next
    INDEX
    Explanations

    mentions of official announcements or information

    oai_token-act-pair · gpt-3.5-turbo

    references to official sources or documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    esville
    -0.94
    ĸļ
    -0.87
    ï¸
    -0.87
    bane
    -0.82
    ocene
    -0.80
    xual
    -0.79
    lust
    -0.77
    Õ
    -0.77
    =-=-
    -0.76
    ertodd
    -0.74
    POSITIVE LOGITS
     sanctioned
    0.91
    dom
    0.88
     confirmation
    0.85
     announcement
    0.85
     spokes
    0.82
     sanction
    0.76
     documentation
    0.75
     official
    0.75
     representative
    0.73
     acknowledgement
    0.73
    Activations Density 0.044%

    No Known Activations