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. 1-RES-JB
    6. 13770
    Prev
    Next
    INDEX
    Explanations

    references to contests or promotions, particularly those involving giveaways as prizes

    oai_token-act-pair · gpt-3.5-turbo

    mentions of giveaways or contests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Xi
    -0.75
    sic
    -0.74
    kes
    -0.71
    pton
    -0.68
    ILL
    -0.66
    OTT
    -0.66
    sis
    -0.65
     Bie
    -0.63
    anti
    -0.63
     Ferr
    -0.63
    POSITIVE LOGITS
     giveaway
    1.49
     giveaways
    1.33
    eers
    0.82
     recip
    0.81
     Give
    0.76
    aways
    0.76
    stakes
    0.75
    affle
    0.70
    breaker
    0.70
     contest
    0.68
    Activations Density 0.011%

    No Known Activations