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. 0-RES-JB
    6. 3704
    Prev
    Next
    INDEX
    Explanations

    words related to neckwear, specifically neckties

    oai_token-act-pair · gpt-3.5-turbo

    references to ties and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ramp
    -0.60
     Pal
    -0.58
     Sprint
    -0.58
    AP
    -0.58
     naked
    -0.57
     Ford
    -0.57
     efficient
    -0.56
     mindful
    -0.56
    olan
    -0.55
     Shutterstock
    -0.55
    POSITIVE LOGITS
    ties
    5.28
    tie
    1.68
    ty
    1.48
    izations
    1.43
    ities
    1.40
    tions
    1.32
    eties
    1.25
    isations
    1.19
    ts
    1.09
    geries
    1.04
    Activations Density 0.014%

    No Known Activations