© 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. 3473
    Prev
    Next
    INDEX
    Explanations

    words related to a particular musician, possibly a rapper, and related topics like music, criticism, and fame

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "agg" and its variations related to a specific subject or topic

    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
    hua
    -0.68
    \\\\\\\\\\\\\\\\
    -0.65
    İĭ
    -0.60
    cki
    -0.58
     stakes
    -0.58
    coming
    -0.58
    Ult
    -0.57
    spect
    -0.55
    nces
    -0.55
    ãĥķãĤ¡
    -0.55
    POSITIVE LOGITS
    ernaut
    1.19
    regate
    1.07
    arette
    1.03
    iano
    1.01
    raph
    0.99
    inson
    0.95
    alos
    0.91
    idy
    0.90
    regation
    0.86
    oths
    0.85
    Activations Density 0.060%

    No Known Activations