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. 1-RES-JB
    6. 15022
    Prev
    Next
    INDEX
    Explanations

    words related to sports teams or animals

    oai_token-act-pair · gpt-3.5-turbo

    terms related to sports teams and their performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ¼ãĥ³
    -0.72
    ASED
    -0.66
    ãĤ¨ãĥ«
    -0.66
     scientific
    -0.61
     joint
    -0.61
    EG
    -0.61
    PA
    -0.60
    nec
    -0.60
    yss
    -0.59
    aton
    -0.59
    POSITIVE LOGITS
    ervatives
    1.33
    poons
    1.27
    paces
    1.20
    kies
    1.04
    uggest
    1.03
    hip
    1.02
    mith
    1.01
    hips
    1.01
    aurus
    0.97
    ervative
    0.97
    Activations Density 0.163%

    No Known Activations