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. 22197
    Prev
    Next
    INDEX
    Explanations

    mentions of the media organization "ABC"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the ABC network

    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
    irts
    -0.77
    wagen
    -0.72
    amoto
    -0.71
     Hiroshima
    -0.70
    boarding
    -0.69
    vik
    -0.68
    agues
    -0.67
    ainer
    -0.65
    crop
    -0.65
    umatic
    -0.65
    POSITIVE LOGITS
    DEF
    1.37
    NEWS
    0.87
    IRO
    0.85
     ABC
    0.81
    nect
    0.77
     Mub
    0.76
    IS
    0.76
    DF
    0.75
    ABC
    0.75
    ERG
    0.72
    Activations Density 0.005%

    No Known Activations