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. 10898
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to the name "Venona"

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Ven" and variations of it, likely linked to places, events, or concepts associated with Venice

    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
     actionGroup
    -0.91
    intosh
    -0.85
    ARR
    -0.77
    dash
    -0.77
    matically
    -0.75
    VALUE
    -0.75
    è¦ļéĨĴ
    -0.71
    è£ħ
    -0.68
     sled
    -0.68
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.68
    POSITIVE LOGITS
    apore
    0.94
    Ven
    0.94
    ison
    0.86
     Ven
    0.86
    ues
    0.86
    ango
    0.83
    emia
    0.82
    ectomy
    0.78
    enum
    0.78
    cius
    0.77
    Activations Density 0.021%

    No Known Activations