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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 956
    Prev
    Next
    INDEX
    Explanations

    information related to specific numerical figures

    oai_token-act-pair · gpt-3.5-turbo

    significant data trends and patterns over time

    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
     thirst
    -0.55
    minecraft
    -0.52
    lihood
    -0.50
     tray
    -0.50
     buttons
    -0.49
     pans
    -0.48
     clipboard
    -0.48
     Minion
    -0.47
    craft
    -0.47
    vec
    -0.46
    POSITIVE LOGITS
    bernatorial
    0.69
     revised
    0.65
    imester
    0.63
    cember
    0.60
     Reincarn
    0.58
     onwards
    0.57
    ategory
    0.55
    arij
    0.54
     coincide
    0.52
     coincided
    0.51
    Activations Density 1.597%

    No Known Activations