© 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. 10-RES-JB
    11. 16523
    Prev
    Next
    INDEX
    Explanations

    words related to filtering or selective processes

    oai_token-act-pair · gpt-3.5-turbo

    references to filtering mechanisms and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ciating
    -0.78
    erald
    -0.71
    arrass
    -0.66
    ington
    -0.64
    olars
    -0.63
    ocamp
    -0.62
     Legends
    -0.62
    eanor
    -0.62
    lished
    -0.61
    aving
    -0.61
    POSITIVE LOGITS
     filter
    0.99
     filters
    0.95
    filter
    0.94
     filtering
    0.87
     Filter
    0.81
     cutoff
    0.80
    operator
    0.79
    Filter
    0.78
    ters
    0.78
     filtered
    0.76
    Activations Density 0.044%

    No Known Activations