© 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. 21887
    Prev
    Next
    INDEX
    Explanations

    references to someone being associated or connected with a particular situation or event

    oai_token-act-pair · gpt-3.5-turbo

    references to involvement in various activities or events

    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
    ampa
    -0.64
    xious
    -0.64
    TI
    -0.62
    oS
    -0.58
    eming
    -0.58
    heit
    -0.58
     Gleaming
    -0.57
    nova
    -0.57
    ãĤª
    -0.56
    edom
    -0.56
    POSITIVE LOGITS
     in
    0.93
     with
    0.87
     therein
    0.82
    ioned
    0.72
     actively
    0.68
     milit
    0.67
    olved
    0.67
     herein
    0.63
     involved
    0.61
     prominently
    0.60
    Activations Density 0.060%

    No Known Activations