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. 19192
    Prev
    Next
    INDEX
    Explanations

    specific patterns related to online usernames or player profiles

    oai_token-act-pair · gpt-3.5-turbo

    numeric identifiers and related game statistics

    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
    risome
    -0.65
     unsustainable
    -0.64
     landfill
    -0.64
     warehouses
    -0.64
     curtail
    -0.63
     destabil
    -0.63
     crippling
    -0.63
     highways
    -0.62
     airspace
    -0.61
     attRot
    -0.60
    POSITIVE LOGITS
    ername
    0.97
     whom
    0.83
    who
    0.80
    username
    0.78
     Cosponsors
    0.74
     avatar
    0.74
    escription
    0.74
    ACTED
    0.72
     surname
    0.72
     Username
    0.71
    Activations Density 0.725%

    No Known Activations