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. 10-RES-JB
    6. 17131
    Prev
    Next
    INDEX
    Explanations

    names, particularly surnames

    oai_token-act-pair · gpt-3.5-turbo

    references to entities or names associated with significant events or individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    llah
    -0.72
    OPLE
    -0.66
    merce
    -0.61
    Downloadha
    -0.55
    URR
    -0.55
    dayName
    -0.54
     itch
    -0.53
     multiplier
    -0.53
     intimidating
    -0.52
     thous
    -0.52
    POSITIVE LOGITS
    emort
    1.04
    uania
    1.03
    gren
    0.93
    heed
    0.89
    oyd
    0.85
    cious
    0.84
    akia
    0.83
    emouth
    0.83
    uli
    0.83
    thening
    0.82
    Activations Density 0.074%

    No Known Activations