© 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. 7-RES-JB
    11. 19091
    Prev
    Next
    INDEX
    Explanations

    the word "tut" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the word "tut" or closely related variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etheus
    -0.78
    nect
    -0.77
    perse
    -0.72
    wcs
    -0.70
    agher
    -0.67
    ĪĴ
    -0.67
    ppelin
    -0.66
    oreal
    -0.66
    aline
    -0.65
    daq
    -0.63
    POSITIVE LOGITS
    tle
    1.21
    ierrez
    1.16
    TING
    0.98
    ting
    0.96
    ted
    0.89
    te
    0.88
    ilities
    0.87
    chell
    0.86
    glers
    0.86
    su
    0.86
    Activations Density 0.065%

    No Known Activations