© 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. 11-RES-JB
    11. 7435
    Prev
    Next
    INDEX
    Explanations

    phrases related to initial impressions or first encounters

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating initial impressions or reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    rolet
    -0.84
    ashington
    -0.66
    ux
    -0.63
    Ñĭ
    -0.62
    RAM
    -0.62
    laws
    -0.60
     Accessories
    -0.59
    efe
    -0.58
     Journals
    -0.58
    Stat
    -0.58
    POSITIVE LOGITS
     glance
    1.95
     blush
    1.75
     sight
    1.41
     glimpse
    1.09
     Sight
    0.96
     impression
    0.96
     glances
    0.87
     responders
    0.86
     impressions
    0.83
    sight
    0.82
    Activations Density 0.037%

    No Known Activations