© 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. 21583
    Prev
    Next
    INDEX
    Explanations

    phrases related to carrying out actions or plans

    oai_token-act-pair · gpt-3.5-turbo

    terms related to execution or the act of carrying out plans

    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
    stice
    -0.68
    eeks
    -0.64
    pmwiki
    -0.64
    iliation
    -0.64
    ateur
    -0.62
    oult
    -0.61
    idding
    -0.59
    earch
    -0.59
     Reboot
    -0.58
     Seym
    -0.58
    POSITIVE LOGITS
     forward
    0.97
    forward
    0.93
     out
    0.92
    out
    0.89
     heavier
    0.79
     weight
    0.77
     loads
    0.75
     onward
    0.75
    over
    0.74
     torches
    0.73
    Activations Density 0.075%

    No Known Activations