© 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. 11264
    Prev
    Next
    INDEX
    Explanations

    phrases related to taking action or exerting influence

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate actions or events involving accountability or responsibility

    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
    there
    -0.73
    usa
    -0.67
    WR
    -0.64
    ACC
    -0.63
    orp
    -0.62
    wake
    -0.62
    eree
    -0.61
     Unloaded
    -0.61
    HC
    -0.60
    chan
    -0.60
    POSITIVE LOGITS
     regards
    1.22
     impunity
    1.18
     vig
    1.10
     gust
    1.06
     regard
    1.03
     ease
    0.97
     respect
    0.96
     tales
    0.96
     promises
    0.94
    draw
    0.93
    Activations Density 0.140%

    No Known Activations