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. 3-RES-JB
    6. 14179
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "swag" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    words related to food and drinking

    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
    ij士
    -0.72
    ©¶æ
    -0.69
    ICAN
    -0.67
    »Ĵ
    -0.67
     pse
    -0.65
     shin
    -0.65
    -+-+
    -0.63
    minus
    -0.63
    BIL
    -0.62
    querque
    -0.62
    POSITIVE LOGITS
    interstitial
    0.86
    ibaba
    0.82
    itives
    0.73
    ishly
    0.72
    agger
    0.71
    bucks
    0.71
    inki
    0.70
    river
    0.70
    iland
    0.70
    ombat
    0.69
    Activations Density 0.048%

    No Known Activations