© 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. 3881
    Prev
    Next
    INDEX
    Explanations

    words related to brewing and breweries

    oai_token-act-pair · gpt-3.5-turbo

    references to brewing and beer

    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
    ively
    -0.96
    olson
    -0.77
    oses
    -0.67
    arette
    -0.67
    ograph
    -0.67
     cuff
    -0.66
    ography
    -0.66
    alian
    -0.65
     Burgess
    -0.64
     Figures
    -0.64
    POSITIVE LOGITS
    ts
    1.00
    ging
    0.99
    ten
    0.97
    ties
    0.95
    terness
    0.94
    pub
    0.93
    tted
    0.92
    caster
    0.91
    gment
    0.90
    eries
    0.90
    Activations Density 0.087%

    No Known Activations