© 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 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. 10-RES-JB
    11. 3312
    Prev
    Next
    INDEX
    Explanations

    the word "Bon" along with variations of it at varying strengths of activation

    oai_token-act-pair · gpt-3.5-turbo

    the brand name "Bon" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ODE
    -0.68
    ELD
    -0.67
    dfx
    -0.66
    INAL
    -0.65
    REAM
    -0.61
    LER
    -0.60
     Ethics
    -0.59
     Editorial
    -0.58
     fluids
    -0.58
    AY
    -0.57
    POSITIVE LOGITS
    anza
    1.32
    uses
    1.09
    kers
    1.08
    obos
    1.04
    eless
    1.03
    nie
    1.03
    iton
    1.03
    anz
    1.01
    bon
    1.00
    gey
    0.99
    Activations Density 0.022%

    No Known Activations