© 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. 8-RES-JB
    11. 20401
    Prev
    Next
    INDEX
    Explanations

    adjectives describing the magnitude or intensity of something

    oai_token-act-pair · gpt-3.5-turbo

    adjectives indicating the scale, clarity, or magnitude of issues

    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
     Flavoring
    -0.90
    mosp
    -0.71
    ochond
    -0.70
    icrobial
    -0.68
    deen
    -0.64
     bow
    -0.60
    rador
    -0.60
    ortment
    -0.58
    ymes
    -0.58
    tein
    -0.58
    POSITIVE LOGITS
     enough
    1.00
     compared
    0.82
     nonetheless
    0.79
    ;
    0.78
    .
    0.77
    enough
    0.76
     regardless
    0.71
     nevertheless
    0.70
    izable
    0.69
    stated
    0.69
    Activations Density 0.302%

    No Known Activations