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. 11-RES-JB
    6. 4530
    Prev
    Next
    INDEX
    Explanations

    words related to locations or entities with "ara" in them

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "Dara" and variations of Arabic names and terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rium
    -0.65
    ullivan
    -0.64
    lor
    -0.63
    TRY
    -0.63
    rer
    -0.62
    regor
    -0.62
    lers
    -0.62
    LER
    -0.61
    rers
    -0.59
    low
    -0.59
    POSITIVE LOGITS
    uthor
    1.13
    ï
    0.97
    ishi
    0.89
    esthetic
    0.86
    qual
    0.86
    esthesia
    0.85
    heed
    0.85
    illac
    0.84
    resh
    0.83
    ean
    0.82
    Activations Density 0.098%

    No Known Activations