Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 18044
    Prev
    Next
    INDEX
    Explanations

    occurrences of the phrase "ter" followed by a number, potentially indicating a technical term or measurement

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "terabyte" and references to spatial data or imaging

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ELS
    -0.79
    orship
    -0.79
    OWS
    -0.75
    issance
    -0.73
    Downloadha
    -0.72
    ":"/
    -0.71
    enhagen
    -0.70
    olitan
    -0.70
    hetti
    -0.70
    ortium
    -0.69
    POSITIVE LOGITS
    rigan
    1.00
    ranean
    0.97
    abytes
    0.97
    mite
    0.91
    abyte
    0.91
    rible
    0.88
    bour
    0.87
    race
    0.87
    rors
    0.87
    rance
    0.85
    Activations Density 0.008%

    No Known Activations