© 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. 21126
    Prev
    Next
    INDEX
    Explanations

    occurances of the word "Bab" with a varying activation level for each number

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Bab" in various contexts

    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
     gard
    -0.65
     REPORT
    -0.63
     mesh
    -0.61
     Ceres
    -0.60
     Copenhagen
    -0.59
    ICES
    -0.58
    âĶĢâĶĢ
    -0.58
     Frey
    -0.58
     Californ
    -0.57
     Fargo
    -0.57
    POSITIVE LOGITS
    cock
    1.13
    ylon
    1.05
    alon
    0.97
    raham
    0.97
    ush
    0.97
    yl
    0.91
    aji
    0.91
    amia
    0.86
    ies
    0.86
    lov
    0.85
    Activations Density 0.029%

    No Known Activations