© 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. 18513
    Prev
    Next
    INDEX
    Explanations

    the word "volume" and variations of it

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "blume."

    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
    fram
    -0.64
    umenthal
    -0.60
     cradle
    -0.59
    actionDate
    -0.59
    ansom
    -0.57
    Mini
    -0.57
     sorely
    -0.57
     Charter
    -0.56
     hect
    -0.55
    ulation
    -0.55
    POSITIVE LOGITS
    umes
    1.11
    ume
    1.01
    OPLE
    0.92
    iture
    0.87
    uming
    0.87
    ose
    0.83
    udi
    0.82
    urs
    0.77
    UME
    0.74
    nil
    0.72
    Activations Density 0.019%

    No Known Activations