© 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. 2-RES-JB
    11. 18360
    Prev
    Next
    INDEX
    Explanations

    references to medical doctors (MD) of various levels or mentions of medical documents

    oai_token-act-pair · gpt-3.5-turbo

    references to medical degrees or qualifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    =-=-=-=-=-=-=-=-
    -0.89
    toggle
    -0.87
    flies
    -0.83
     Sabha
    -0.83
    ãĥ¼ãĥ³
    -0.80
    bidden
    -0.80
    acters
    -0.80
    berus
    -0.76
    angered
    -0.76
    nel
    -0.76
    POSITIVE LOGITS
    iamond
    0.92
    ouble
    0.84
    MD
    0.84
     MD
    0.79
     condem
    0.75
    enture
    0.73
    ription
    0.73
    aughter
    0.70
    NF
    0.69
    irect
    0.67
    Activations Density 0.003%

    No Known Activations