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. 11-RES-JB
    6. 18313
    Prev
    Next
    INDEX
    Explanations

    specific technical terms and concepts related to data, information, or tasks at hand

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to societal issues and structural components of communities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zek
    -0.72
    DragonMagazine
    -0.64
    DW
    -0.63
    luaj
    -0.59
    zeb
    -0.57
     Peaks
    -0.57
    cffffcc
    -0.56
     summers
    -0.55
     Saiyan
    -0.55
    BuyableInstoreAndOnline
    -0.54
    POSITIVE LOGITS
     itself
    1.28
     involved
    0.96
     depicted
    0.95
     owner
    0.92
     recipient
    0.91
     chosen
    0.91
     specified
    0.90
     oneself
    0.90
    owner
    0.89
    (
    0.89
    Activations Density 0.457%

    No Known Activations