© 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. 3416
    Prev
    Next
    INDEX
    Explanations

    occurrences of the phrase "at all" in sentences

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the expression "at all"

    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
    ãģ®éŃĶ
    -0.63
     Ahead
    -0.62
    izo
    -0.62
    pez
    -0.61
    adr
    -0.60
    sett
    -0.59
    OTA
    -0.57
    ascript
    -0.57
    orio
    -0.57
    onymous
    -0.56
    POSITIVE LOGITS
     all
    1.46
     ALL
    1.18
    all
    1.03
    All
    0.95
     All
    0.94
    onement
    0.90
     least
    0.89
     anytime
    0.89
     ali
    0.86
     any
    0.82
    Activations Density 0.063%

    No Known Activations