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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9-RES-JB
    11. 408
    Prev
    Next
    INDEX
    Explanations

    instinct-related words and phrases

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to instinct and desire

    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
    mbuds
    -0.89
    mberg
    -0.83
    atari
    -0.76
    arer
    -0.74
    Arab
    -0.72
    ensis
    -0.71
    arers
    -0.71
    gow
    -0.70
    hw
    -0.70
    cup
    -0.70
    POSITIVE LOGITS
     impulse
    1.11
     urge
    1.02
     impulses
    1.00
     temptation
    1.00
     toward
    0.97
     instinct
    0.94
     reaction
    0.91
     urges
    0.90
     instinctively
    0.90
     towards
    0.87
    Activations Density 0.091%

    No Known Activations