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. 3-RES-JB
    6. 18967
    Prev
    Next
    INDEX
    Explanations

    phrases related to contests or events where items are given away for free

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of "giveaway" and related giveaway terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sis
    -0.72
    kes
    -0.71
     Bie
    -0.70
    acci
    -0.70
    angelo
    -0.68
    Xi
    -0.66
    bian
    -0.66
    Li
    -0.65
    kos
    -0.65
    steen
    -0.64
    POSITIVE LOGITS
     giveaway
    1.28
     giveaways
    1.14
    eers
    0.76
     gif
    0.75
    affle
    0.75
    aways
    0.75
     receipts
    0.73
     prizes
    0.72
    stakes
    0.71
     subsidy
    0.67
    Activations Density 0.014%

    No Known Activations