© 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. 10757
    Prev
    Next
    INDEX
    Explanations

    terminology related to filters, such as filter material, installing filters, and different types of filters

    oai_token-act-pair · gpt-3.5-turbo

    references to filtering mechanisms or filters

    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
    ciating
    -0.79
    eanor
    -0.77
    olars
    -0.68
    ILY
    -0.68
    nee
    -0.64
    rious
    -0.63
    arrass
    -0.62
    roach
    -0.62
     Herald
    -0.61
    avement
    -0.61
    POSITIVE LOGITS
    filter
    0.88
     filters
    0.88
    operator
    0.85
     filter
    0.85
     filtering
    0.78
     Filter
    0.77
     cutoff
    0.76
    door
    0.74
     sweeps
    0.72
    arette
    0.69
    Activations Density 0.034%

    No Known Activations