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. 11088
    Prev
    Next
    INDEX
    Explanations

    phrases expressing strong positive sentiment

    oai_token-act-pair · gpt-3.5-turbo

    expressions of affection or admiration

    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
    merce
    -0.77
    icter
    -0.75
    iban
    -0.75
    ramid
    -0.74
     reluct
    -0.73
    ulhu
    -0.73
    enei
    -0.73
    interstitial
    -0.72
    SPONSORED
    -0.72
    thren
    -0.71
    POSITIVE LOGITS
    birds
    1.03
    joy
    0.89
     uncond
    0.89
     dearly
    0.88
    fully
    0.85
     passionately
    0.81
    bird
    0.74
     Loving
    0.72
     LOVE
    0.72
    tsky
    0.72
    Activations Density 0.032%

    No Known Activations