Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 1314
    Prev
    Next
    INDEX
    Explanations

    physical activities and locations where they occur

    oai_token-act-pair · gpt-3.5-turbo

    activities or events that involve playing or sports-related actions

    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
     pestic
    -0.62
    mbuds
    -0.60
    stood
    -0.55
    ificant
    -0.54
    TPPStreamerBot
    -0.53
    ¿½
    -0.52
     Thumbnails
    -0.51
     definitively
    -0.51
     categ
    -0.50
    ļé
    -0.50
    POSITIVE LOGITS
     whilst
    0.68
     alongside
    0.68
     respectively
    0.67
     while
    0.65
    worms
    0.63
     fame
    0.63
    worm
    0.63
     raping
    0.62
     overlooking
    0.60
     pretending
    0.60
    Activations Density 0.802%

    No Known Activations