© 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. 6-RES-JB
    11. 14014
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Bi" or "Biotechnology"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific biomedical entities and terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ments
    -0.95
    enance
    -0.79
    MENTS
    -0.74
     lobe
    -0.73
    swick
    -0.72
     tune
    -0.71
    manship
    -0.71
     actionGroup
    -0.70
    eering
    -0.69
    mable
    -0.69
    POSITIVE LOGITS
    otech
    0.88
    ogenesis
    0.87
    ologists
    0.87
    alez
    0.82
    omorph
    0.82
    omedical
    0.81
    ologically
    0.81
    olia
    0.80
    agame
    0.80
    isine
    0.80
    Activations Density 0.031%

    No Known Activations