© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 998
    Prev
    Next
    INDEX
    Explanations

    words related to instincts and instinctive behaviors

    oai_token-act-pair · gpt-3.5-turbo

    references to instincts and instinctive behavior

    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
    annis
    -0.76
    paces
    -0.73
    kees
    -0.72
    leaf
    -0.71
    gard
    -0.71
    sted
    -0.70
     Accounting
    -0.70
    qa
    -0.68
    gur
    -0.68
    forestation
    -0.68
    POSITIVE LOGITS
     instinct
    1.25
     instinctively
    1.10
     reflex
    1.08
     impulse
    1.06
     instincts
    1.04
     reaction
    1.04
     urge
    1.03
     impulses
    1.03
    ual
    0.99
     reactions
    0.93
    Activations Density 0.083%

    No Known Activations