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. 15595
    Prev
    Next
    INDEX
    Explanations

    words related to physical appearance or traits

    oai_token-act-pair · gpt-3.5-turbo

    suffixes and endings commonly associated with certain adjectives and nouns, particularly in derogatory or informal contexts

    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
    soDeliveryDate
    -0.91
     Sabha
    -0.85
     Skydragon
    -0.82
    ãĥ³ãĤ¸
    -0.72
    âĹ¼
    -0.70
    anguage
    -0.68
    éŃĶ
    -0.67
    Motor
    -0.67
    ItemThumbnailImage
    -0.67
     Compass
    -0.67
    POSITIVE LOGITS
    ruary
    1.03
    ancial
    0.95
     sake
    0.80
    rency
    0.79
    ulent
    0.76
    cially
    0.74
    gotten
    0.67
    ilial
    0.64
    idious
    0.64
     du
    0.64
    Activations Density 0.095%

    No Known Activations