© 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. 3495
    Prev
    Next
    INDEX
    Explanations

    statements related to denying involvement or taking steps to prevent certain actions

    oai_token-act-pair · gpt-3.5-turbo

    statements of denial or non-involvement

    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
     hailed
    -0.68
    ufact
    -0.68
     nonetheless
    -0.65
    ptoms
    -0.65
    surprisingly
    -0.64
     beware
    -0.62
    uers
    -0.61
     plenty
    -0.61
     realise
    -0.61
    surv
    -0.60
    POSITIVE LOGITS
     nor
    1.21
     whatsoever
    1.16
     anybody
    0.96
    partisan
    0.90
     anything
    0.87
     âĢ
    0.87
     [
    0.85
    âĢİ
    0.80
     âĢ¦"
    0.80
     prejud
    0.78
    Activations Density 0.427%

    No Known Activations