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

    Neuronpedia

    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. 6-RES-JB
    11. 1510
    Prev
    Next
    INDEX
    Explanations

    references to things related to the term "BB" as well as medical or physiological terms

    oai_token-act-pair · gpt-3.5-turbo

    references to blood-brain barrier-related terms or concepts

    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
    izational
    -0.92
    bourg
    -0.90
    perse
    -0.88
    ources
    -0.85
    izations
    -0.82
    endez
    -0.81
    ional
    -0.77
    pora
    -0.76
    isations
    -0.73
    isation
    -0.73
    POSITIVE LOGITS
    BB
    0.99
    ATH
    0.85
    ruary
    0.82
    ERN
    0.75
    HK
    0.74
    uild
    0.73
    irds
    0.72
    ONY
    0.72
    NF
    0.70
    ooth
    0.69
    Activations Density 0.023%

    No Known Activations