© 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. 9-RES-JB
    11. 11465
    Prev
    Next
    INDEX
    Explanations

    references to formal or official statements or declarations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "The."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cum
    -0.80
    lled
    -0.72
     aka
    -0.71
    ãĤ´ãĥ³
    -0.71
    !.
    -0.70
    *.
    -0.70
    /"
    -0.70
    Ò
    -0.69
    android
    -0.68
    kai
    -0.67
    POSITIVE LOGITS
    resa
    1.26
    oret
    1.14
     notion
    1.10
     idea
    1.08
     importance
    1.02
     purpose
    1.01
     aim
    1.00
     greatest
    0.99
     biggest
    0.98
     implication
    0.97
    Activations Density 0.281%

    No Known Activations