© 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. 2371
    Prev
    Next
    INDEX
    Explanations

    words related to disasters or catastrophic events

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "cat" and its variations in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words containing 'cat' or related to cats.

    Explanation Uploaded by User
    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
    OND
    -0.70
    ij士
    -0.65
    unda
    -0.62
    ashtra
    -0.59
    hower
    -0.59
     rece
    -0.58
     Ug
    -0.58
    FontSize
    -0.58
    ESH
    -0.58
    indal
    -0.57
    POSITIVE LOGITS
    aclysm
    1.57
    heter
    1.38
    apult
    1.31
    chers
    1.23
    alogue
    1.21
    alyst
    1.21
    cher
    1.14
    fish
    1.09
    hedral
    1.09
    alog
    1.09
    Activations Density 0.033%

    No Known Activations