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. 8516
    Prev
    Next
    INDEX
    Explanations

    words related to transportation vehicles and containers

    oai_token-act-pair · gpt-3.5-turbo

    words related to vehicles and containers used for transport

    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
    âĸ¬
    -0.88
    ãĤ´ãĥ³
    -0.76
    ĻĤ
    -0.71
    nesota
    -0.70
    ãĥį
    -0.70
    Synopsis
    -0.68
    Transaction
    -0.67
    liest
    -0.66
    ãĥ´
    -0.65
    AE
    -0.65
    POSITIVE LOGITS
    mith
    1.27
    poons
    1.11
    hips
    1.08
    creen
    1.05
    leeve
    1.02
    ongs
    1.02
     stacked
    0.99
    hops
    0.98
    avers
    0.95
    paces
    0.95
    Activations Density 0.192%

    No Known Activations