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

    Neuronpedia

    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. 17243
    Prev
    Next
    INDEX
    Explanations

    conjunctions followed by a verb or noun

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" indicating connections or relationships between ideas or actions

    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
    Tes
    -0.78
    rb
    -0.73
    agon
    -0.66
    ibble
    -0.65
    HAM
    -0.64
    bub
    -0.64
    FL
    -0.63
    219
    -0.63
    hub
    -0.61
    ction
    -0.61
    POSITIVE LOGITS
     assorted
    1.20
     finally
    1.15
     ultimately
    1.03
     downright
    0.98
     possibly
    0.96
     optionally
    0.89
     frankly
    0.88
     consequently
    0.88
     perhaps
    0.85
     occasionally
    0.82
    Activations Density 0.156%

    No Known Activations