© 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. 4-RES-JB
    11. 7222
    Prev
    Next
    INDEX
    Explanations

    medical and anatomical terms related to the colon

    oai_token-act-pair · gpt-3.5-turbo

    references to specific ailments or conditions related to the digestive system

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

    No Comments

    Negative Logits
    âĶģ
    -0.83
    immune
    -0.69
    reditary
    -0.69
    ricks
    -0.69
    OTOS
    -0.69
    ynski
    -0.68
    ratulations
    -0.68
     Pwr
    -0.67
    uyomi
    -0.67
    ocre
    -0.67
    POSITIVE LOGITS
    igm
    0.77
     col
    0.76
    ciating
    0.75
    pex
    0.71
    iop
    0.71
    uin
    0.70
    itudinal
    0.70
    inois
    0.69
    iage
    0.68
    ousing
    0.66
    Activations Density 0.017%

    No Known Activations