© 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. 7-RES-JB
    11. 23068
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Brad"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Brad."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     postage
    -0.68
     wiret
    -0.67
     versa
    -0.66
     subsistence
    -0.66
     referen
    -0.65
    ktop
    -0.65
     condol
    -0.65
     payable
    -0.65
     derog
    -0.65
     recalling
    -0.63
    POSITIVE LOGITS
    shaw
    1.28
    enton
    1.17
    ford
    1.04
     Pitt
    0.94
    rill
    0.92
    ney
    0.87
    burn
    0.87
    street
    0.85
    gewater
    0.83
    mund
    0.83
    Activations Density 0.017%

    No Known Activations