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. 20923
    Prev
    Next
    INDEX
    Explanations

    words related to statistical findings and analysis

    oai_token-act-pair · gpt-3.5-turbo

    significant statistical correlations and associations in research findings

    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
    iquette
    -0.77
    cms
    -0.74
     commons
    -0.72
    Mist
    -0.71
    ä¸Ĭ
    -0.69
    wire
    -0.69
    ç«
    -0.69
    cour
    -0.69
    roots
    -0.68
    fare
    -0.67
    POSITIVE LOGITS
     (âĪĴ
    1.21
     detectable
    0.94
     correlated
    0.91
     statistically
    0.91
     heterogeneity
    0.90
    itivity
    0.89
     antidepressant
    0.89
     serum
    0.89
     clinically
    0.85
     antibody
    0.85
    Activations Density 0.251%

    No Known Activations