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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9-RES-JB
    6. 6597
    Prev
    Next
    INDEX
    Explanations

    words or short expressions starting with "Fr" followed by a vowel and/or consonant

    oai_token-act-pair · gpt-3.5-turbo

    instances of the name "Fr" or variations referencing "Fr" as a prefix, indicating a focus on geographical or contextual relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Siren
    -0.71
     Jinn
    -0.71
     arteries
    -0.66
     Izan
    -0.65
    orney
    -0.63
     destro
    -0.61
    izu
    -0.60
    fram
    -0.59
     Khe
    -0.58
    weapons
    -0.58
    POSITIVE LOGITS
    isco
    0.92
    furt
    0.76
    ulent
    0.74
    ruary
    0.72
    rance
    0.71
    liest
    0.66
    ophile
    0.64
    ateur
    0.60
    ateurs
    0.60
    bees
    0.59
    Activations Density 0.118%

    No Known Activations