© 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. 12-RES-JB
    11. 3525
    Prev
    Next
    INDEX
    Explanations

    miscellaneous and seemingly unrelated snippets of text rather than a specific theme or pattern

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    colons and times, indicating structured information or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
     comm
    -0.60
     outright
    -0.59
     operation
    -0.58
     snap
    -0.57
     legitimately
    -0.56
     disagree
    -0.56
     flat
    -0.55
    ...
    -0.55
     benef
    -0.55
     outl
    -0.55
    POSITIVE LOGITS
    ©¶æ
    0.87
     pione
    0.80
     Transcript
    0.75
     Encyclopedia
    0.75
    lished
    0.75
    ą
    0.74
    ě
    0.74
    Ď
    0.73
    ė
    0.73
    ē
    0.73
    Activations Density 0.045%

    No Known Activations