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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 12-RES-JB
    6. 6967
    Prev
    Next
    INDEX
    Explanations

    phrases related to events, announcements, and procedures

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    expressions of personal struggle or vulnerability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     policing
    -0.61
     Winston
    -0.58
     Wilmington
    -0.57
     legality
    -0.57
     Prometheus
    -0.56
     Revolution
    -0.56
     Greens
    -0.56
     graphene
    -0.55
     revolutionaries
    -0.55
     politics
    -0.55
    POSITIVE LOGITS
    t
    0.99
    itely
    0.98
    ¨
    0.94
    tions
    0.93
    tion
    0.90
    £
    0.88
    Ľ
    0.87
    ª
    0.86
    »
    0.86
    ĸ
    0.86
    Activations Density 0.061%

    No Known Activations