© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 24388
    Prev
    Next
    INDEX
    Explanations

    terms related to medical research and cell localization

    oai_token-act-pair · gpt-3.5-turbo

    references to specific types of cells and their scientific observations or experimental results

    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
    conom
    -0.84
     someday
    -0.80
    profits
    -0.75
    estate
    -0.71
    ___
    -0.69
     ..."
    -0.68
     lately
    -0.68
    advertising
    -0.68
    catentry
    -0.67
     yours
    -0.67
    POSITIVE LOGITS
     assay
    1.12
     PCR
    1.12
    RESULTS
    1.06
     stained
    1.02
     purified
    0.95
     supplemented
    0.92
     perf
    0.91
     hist
    0.91
     analysed
    0.90
     analyzed
    0.90
    Activations Density 0.268%

    No Known Activations