© 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. 4-RES-JB
    11. 6971
    Prev
    Next
    INDEX
    Explanations

    terms related to neuroscience and medical studies, specifically focusing on terms like "neuro," "CNS," "pathologies," and "prefrontal cortex."

    oai_token-act-pair · gpt-3.5-turbo

    references to medical conditions and their associations with psychological and physiological traits

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

    No Comments

    Negative Logits
     whine
    -0.70
    VIDEO
    -0.67
     whim
    -0.66
    shit
    -0.65
     Vanity
    -0.65
     dime
    -0.63
    Privacy
    -0.63
    Billy
    -0.63
     condos
    -0.61
     booze
    -0.61
    POSITIVE LOGITS
     âĪ¼
    1.09
     hypothesized
    0.95
     endogenous
    0.92
     analyses
    0.90
     methodological
    0.89
     causal
    0.88
     hypotheses
    0.87
    âĢIJ
    0.86
     quantitative
    0.86
     assay
    0.85
    Activations Density 1.482%

    No Known Activations