© 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. 3-RES-JB
    11. 18298
    Prev
    Next
    INDEX
    Explanations

    phrases, names, and terms related to the name "Ash"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of 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 @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olicy
    -0.89
    rompt
    -0.77
    ktop
    -0.71
    cision
    -0.71
    emort
    -0.70
    etheless
    -0.69
    afort
    -0.68
    plete
    -0.67
    opausal
    -0.67
    İĭ
    -0.67
    POSITIVE LOGITS
    burn
    1.06
    leigh
    1.04
    bourne
    1.02
    bolt
    1.00
    brook
    0.99
     Ash
    0.95
    croft
    0.94
    lee
    0.93
    pak
    0.87
    Ash
    0.86
    Activations Density 0.005%

    No Known Activations