© 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. 0-RES-JB
    11. 10035
    Prev
    Next
    INDEX
    Explanations

    the word "Ash"

    oai_token-act-pair · gpt-3.5-turbo

    the name "Ash" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ificate
    -0.87
    enezuel
    -0.74
    mo
    -0.73
    ulo
    -0.72
    umbo
    -0.71
     Quadro
    -0.71
    Cub
    -0.70
    pload
    -0.70
    ocument
    -0.69
    xe
    -0.66
    POSITIVE LOGITS
     Ash
    3.70
    Ash
    2.79
     ash
    2.06
     Ashton
    1.63
     Ashley
    1.37
     Ashe
    1.31
    ash
    1.20
     Rash
    1.20
     Kir
    1.19
     Ashes
    1.18
    Activations Density 0.020%

    No Known Activations