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. 22146
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial figures and projections

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating numerical figures or statistics related to timeframes

    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
    illary
    -0.90
    uum
    -0.66
    ****************
    -0.65
    MSN
    -0.63
    UE
    -0.62
    KE
    -0.61
    STAR
    -0.61
    uary
    -0.60
    ofi
    -0.59
    Journal
    -0.59
    POSITIVE LOGITS
    hang
    1.09
    loading
    1.07
    drive
    1.01
    priced
    1.00
    lord
    1.00
    whelming
    0.99
    payment
    0.99
    haul
    0.96
    clock
    0.96
    valued
    0.92
    Activations Density 0.090%

    No Known Activations