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. 10-RES-JB
    6. 15563
    Prev
    Next
    INDEX
    Explanations

    patterns related to sorting and organizing data

    oai_token-act-pair · gpt-3.5-turbo

    coordinating conjunctions and their usage in complex sentence structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    meet
    -0.77
    justice
    -0.76
    burgh
    -0.74
    Today
    -0.74
    onica
    -0.73
    anmar
    -0.72
    Meet
    -0.72
    landish
    -0.70
    hoe
    -0.70
    ilo
    -0.69
    POSITIVE LOGITS
     hence
    1.55
     thus
    1.54
     thereby
    1.50
     therefore
    1.49
     vice
    1.45
     optionally
    1.40
     consequently
    1.40
     then
    1.36
     thence
    1.35
     secondly
    1.30
    Activations Density 0.329%

    No Known Activations