© 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. 3972
    Prev
    Next
    INDEX
    Explanations

    the verb "muster"

    oai_token-act-pair · gpt-3.5-turbo

    repeated uses of the word "muster" in various contexts

    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
     Leilan
    -0.75
    apy
    -0.75
    IU
    -0.75
     VICE
    -0.73
    ania
    -0.70
    ricular
    -0.70
    ented
    -0.67
    aned
    -0.65
    vice
    -0.64
    van
    -0.64
    POSITIVE LOGITS
    éĹĺ
    0.92
    ahead
    0.82
    wit
    0.80
    fits
    0.80
    keley
    0.76
     suit
    0.76
    manship
    0.75
    acca
    0.75
     brav
    0.71
     declaration
    0.70
    Activations Density 0.020%

    No Known Activations