© 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 EvalsExportsinterp-engineNEWAPI 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. 12553
    Prev
    Next
    INDEX
    Explanations

    phrases related to speculation about potential outcomes or events

    oai_token-act-pair · gpt-3.5-turbo

    conjectures or hypothetical scenarios regarding consequences or outcomes

    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
    yet
    -0.65
    BuyableInstoreAndOnline
    -0.57
     ado
    -0.56
    Enough
    -0.55
    azo
    -0.51
     Gone
    -0.49
     Yet
    -0.49
    mber
    -0.47
    >)
    -0.47
    emis
    -0.46
    POSITIVE LOGITS
     if
    1.90
     when
    1.47
    when
    1.39
    if
    1.38
     whenever
    1.32
     unless
    1.28
     IF
    1.19
     WHEN
    1.12
    unless
    1.06
     whichever
    1.05
    Activations Density 1.935%

    No Known Activations