© 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. 8-RES-JB
    11. 1146
    Prev
    Next
    INDEX
    Explanations

    phrases indicating determination or commitment

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "no matter" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olis
    -0.91
    ahime
    -0.80
    iens
    -0.77
    berus
    -0.77
    UES
    -0.75
    uctions
    -0.75
    oute
    -0.73
    ischer
    -0.70
    olen
    -0.68
    assi
    -0.68
    POSITIVE LOGITS
     whatsoever
    1.03
     how
    0.85
     respecting
    0.83
     whether
    0.77
     whatever
    0.77
    llor
    0.75
    theless
    0.72
    ¬¼
    0.72
     imaginable
    0.66
     mater
    0.65
    Activations Density 0.015%

    No Known Activations