© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 8-RES-JB
    11. 7844
    Prev
    Next
    INDEX
    Explanations

    verbs related to forceful action or impact

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "bust" and related forms

    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
    esthetic
    -0.74
    velength
    -0.70
    llular
    -0.68
    ndra
    -0.65
     Rouge
    -0.63
    raviolet
    -0.62
    voy
    -0.62
    WAYS
    -0.62
    isable
    -0.62
    rha
    -0.61
    POSITIVE LOGITS
     bust
    0.97
    buster
    0.96
    enegger
    0.86
    aneers
    0.85
    busters
    0.83
    lers
    0.83
    neck
    0.82
    outs
    0.82
    enance
    0.81
    aign
    0.80
    Activations Density 0.031%

    No Known Activations