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. 2362
    Prev
    Next
    INDEX
    Explanations

    percentages and growth rates

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to statistical increases or growth metrics

    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
     staples
    -0.62
    english
    -0.62
    天
    -0.61
    PAR
    -0.60
    ographies
    -0.59
     Nichols
    -0.57
     mant
    -0.57
     Names
    -0.56
     Cabin
    -0.56
    dies
    -0.56
    POSITIVE LOGITS
    xual
    1.11
    over
    0.85
     rate
    0.76
    ait
    0.76
    jriwal
    0.76
    ahead
    0.76
    emaker
    0.76
    onential
    0.75
     subsequ
    0.74
    alore
    0.74
    Activations Density 0.098%

    No Known Activations