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. 9-RES-JB
    6. 14907
    Prev
    Next
    INDEX
    Explanations

    references to specific groups of people or entities, such as teams, kids, or the Canadian prime minister

    oai_token-act-pair · gpt-3.5-turbo

    references to specific groups or teams

    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
    lessly
    -0.68
     namely
    -0.67
    conn
    -0.65
     with
    -0.65
    staking
    -0.65
     preceded
    -0.65
     indeed
    -0.64
    SHIP
    -0.64
     surely
    -0.63
    ication
    -0.63
    POSITIVE LOGITS
     Kardash
    0.89
     devil
    0.86
     buddies
    0.83
     likes
    0.82
     utmost
    0.82
     locals
    0.80
     Russians
    0.78
     fishes
    0.78
     angels
    0.78
     partners
    0.78
    Activations Density 0.356%

    No Known Activations