Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 424
    Prev
    Next
    INDEX
    Explanations

    the keyword 'rest' in various contexts and sentences

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "rest."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gee
    -0.73
    interstitial
    -0.67
    女
    -0.62
     Mahjong
    -0.60
     Blossom
    -0.58
     Ear
    -0.57
    aminer
    -0.56
     Kushner
    -0.56
    FK
    -0.55
    aceae
    -0.55
    POSITIVE LOGITS
    ructure
    1.18
    raint
    1.15
    orative
    1.08
    raints
    1.02
    ricting
    1.01
    ricted
    1.00
    raining
    1.00
    itution
    0.96
    rained
    0.94
    rain
    0.93
    Activations Density 0.014%

    No Known Activations