© 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 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. 14683
    Prev
    Next
    INDEX
    Explanations

    phrases related to communal spaces or gatherings

    oai_token-act-pair · gpt-3.5-turbo

    substrings related to varying forms of the word "miser" and similar suffix variations

    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
    ers
    -0.68
    ering
    -0.66
    ert
    -0.65
     Wish
    -0.64
    ELS
    -0.62
    endor
    -0.62
    heet
    -0.59
    INS
    -0.59
    erman
    -0.59
    EP
    -0.59
    POSITIVE LOGITS
    getic
    1.09
    rors
    1.01
    cial
    1.01
    ror
    0.96
    ÃŃa
    0.94
    rane
    0.93
    gence
    0.90
    atures
    0.88
    imental
    0.87
    ies
    0.86
    Activations Density 0.132%

    No Known Activations