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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 7071
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to intuitive behaviors or reactions

    oai_token-act-pair · gpt-3.5-turbo

    words related to instincts and intuitive actions

    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
    annis
    -0.87
    MET
    -0.79
     Lanka
    -0.76
     Antiqu
    -0.75
    paces
    -0.75
    dule
    -0.73
    qa
    -0.71
    jri
    -0.68
    ouk
    -0.67
    adan
    -0.67
    POSITIVE LOGITS
     instinct
    1.27
    ual
    1.16
     reflex
    1.11
     instinctively
    1.04
     instincts
    1.00
     impulse
    1.00
     reaction
    0.98
     impulses
    0.94
     urge
    0.92
    ually
    0.90
    Activations Density 0.048%

    No Known Activations