© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 15343
    Prev
    Next
    INDEX
    Explanations

    references to meetings or events happening

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Meet," likely indicating an introduction or a reference to a meeting or event

    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
    wcs
    -0.93
    vernment
    -0.78
    secut
    -0.77
     ende
    -0.73
    cffffcc
    -0.71
    ¥ŀ
    -0.70
    cul
    -0.69
    secution
    -0.68
     tiss
    -0.68
     srf
    -0.68
    POSITIVE LOGITS
    ings
    1.09
    ãĤ¤ãĥĪ
    0.98
    INGS
    0.81
     Meet
    0.81
    aunt
    0.79
    amorph
    0.79
    liest
    0.78
    ingly
    0.78
    athon
    0.76
    ups
    0.75
    Activations Density 0.020%

    No Known Activations