© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 5109
    Prev
    Next
    INDEX
    Explanations

    dates and numerical figures related to events

    oai_token-act-pair · gpt-3.5-turbo

    quantitative references to events or statistics

    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
    esses
    -0.91
     Et
    -0.89
     Eck
    -0.87
     Ell
    -0.86
    Ell
    -0.86
     Hess
    -0.85
     ET
    -0.85
    ess
    -0.84
    ELS
    -0.82
    eln
    -0.82
    POSITIVE LOGITS
     1927
    0.85
     269
    0.81
    FP
    0.76
    bor
    0.76
     Josh
    0.75
    ji
    0.73
     1926
    0.72
    Josh
    0.72
    269
    0.72
    Joshua
    0.71
    Activations Density 0.701%

    No Known Activations