© 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. 1-RES-JB
    11. 3449
    Prev
    Next
    INDEX
    Explanations

    medical and scientific terms, specifically those related to physiology and biology

    oai_token-act-pair · gpt-3.5-turbo

    terms related to superficial qualities or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pend
    -0.79
    mint
    -0.75
    gil
    -0.74
    tz
    -0.73
    nesday
    -0.72
    nel
    -0.70
    ãĥ¼ãĥ³
    -0.70
    mand
    -0.69
    mouth
    -0.69
    ment
    -0.69
    POSITIVE LOGITS
     comprom
    0.78
    esthetic
    0.70
    cephal
    0.69
    Cla
    0.67
    rament
    0.66
     nonex
    0.66
     shedding
    0.66
    iability
    0.66
    actic
    0.65
     depreciation
    0.65
    Activations Density 0.020%

    No Known Activations