© 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. 11137
    Prev
    Next
    INDEX
    Explanations

    The neuron looks for mentions related to physical medical examinations

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "mole" or items related to "mole" in various contexts

    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
    ĪĴ
    -0.71
     Rampage
    -0.65
     Lauder
    -0.65
    Redd
    -0.62
     laureate
    -0.61
    writers
    -0.59
     Mous
    -0.59
     depreciation
    -0.58
     Elven
    -0.58
     Repair
    -0.57
    POSITIVE LOGITS
    estation
    1.27
    ossus
    1.08
    asses
    1.06
    icone
    0.99
    esting
    0.98
    untary
    0.95
    onel
    0.94
    estic
    0.93
    esta
    0.93
    oti
    0.93
    Activations Density 0.028%

    No Known Activations