© 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. 10634
    Prev
    Next
    INDEX
    Explanations

    combinations of conditional statements

    oai_token-act-pair · gpt-3.5-turbo

    conditional statements related to potential consequences

    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
    arse
    -0.73
    ved
    -0.70
    acus
    -0.68
    nai
    -0.68
    tained
    -0.66
    atered
    -0.64
    bor
    -0.64
    ve
    -0.63
    inar
    -0.63
    uck
    -0.63
    POSITIVE LOGITS
    will
    0.79
     then
    0.74
     SHALL
    0.74
     will
    0.70
    would
    0.70
    channelAvailability
    0.69
     barring
    0.66
    then
    0.65
     sooner
    0.63
     would
    0.63
    Activations Density 0.260%

    No Known Activations