© 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. 14998
    Prev
    Next
    INDEX
    Explanations

    statements about having enough of something, specifically in relation to achieving a goal or desired outcome

    oai_token-act-pair · gpt-3.5-turbo

    quantities related to financial resources and decision-making factors

    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
    uesday
    -0.74
    asus
    -0.66
    vre
    -0.59
    overe
    -0.56
    ighth
    -0.56
    ometimes
    -0.56
    retty
    -0.55
    ursday
    -0.54
    820
    -0.53
     eBook
    -0.52
    POSITIVE LOGITS
     to
    1.04
     sqor
    0.76
     otherwise
    0.73
     suffice
    0.72
     toget
    0.71
     (>
    0.70
     enough
    0.69
    to
    0.68
     for
    0.68
     outweigh
    0.65
    Activations Density 0.174%

    No Known Activations