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. 8-RES-JB
    6. 22005
    Prev
    Next
    INDEX
    Explanations

    proper names or place names ending in "ano."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "ano"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    matically
    -0.77
    mable
    -0.75
    drawn
    -0.73
    uit
    -0.72
    rants
    -0.71
    manship
    -0.71
    rified
    -0.70
    rir
    -0.69
    TPPStreamerBot
    -0.68
    nah
    -0.67
    POSITIVE LOGITS
    zzi
    1.61
    ÄŁ
    1.16
    jo
    1.02
     Rossi
    0.95
    zzo
    0.94
    ahu
    0.93
    zzle
    0.92
    vernment
    0.88
    ffic
    0.88
    ctor
    0.86
    Activations Density 0.176%

    No Known Activations