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. 3-RES-JB
    6. 7815
    Prev
    Next
    INDEX
    Explanations

    terms related to financial transactions and sports teams

    oai_token-act-pair · gpt-3.5-turbo

    names and terms related to players and teams in soccer

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olitan
    -0.79
    Area
    -0.69
    earable
    -0.61
     outpatient
    -0.58
     pharmacies
    -0.57
     rook
    -0.57
    VALUE
    -0.56
     Syracuse
    -0.56
     shot
    -0.56
     Samoa
    -0.55
    POSITIVE LOGITS
    gaard
    1.10
    theless
    0.99
    lein
    0.97
    lings
    0.97
    gence
    0.95
    rette
    0.94
    nder
    0.90
    holm
    0.90
    ling
    0.89
    ding
    0.88
    Activations Density 0.010%

    No Known Activations