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. 5-RES-JB
    6. 2786
    Prev
    Next
    INDEX
    Explanations

    numbers and technical terms

    oai_token-act-pair · gpt-3.5-turbo

    a mix of numeric values, special characters, and mentions of individuals or locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.68
     glim
    -0.64
     resil
    -0.64
     hindsight
    -0.60
    leck
    -0.58
     leaps
    -0.57
    é¾įåĸļ士
    -0.57
    CRIPTION
    -0.57
    reau
    -0.56
    pedia
    -0.56
    POSITIVE LOGITS
     thirds
    0.62
     choke
    0.55
    ociate
    0.55
    thirds
    0.55
    ukemia
    0.55
     Osc
    0.53
    cheat
    0.52
     Seym
    0.52
    ovych
    0.51
     husband
    0.50
    Activations Density 1.358%

    No Known Activations