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. 4-RES-JB
    6. 331
    Prev
    Next
    INDEX
    Explanations

    references to a specific technology protocol called Transmission Control Protocol (TCP)

    oai_token-act-pair · gpt-3.5-turbo

    references to the Transmission Control Protocol (TCP)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥĢ
    -0.86
    hold
    -0.81
     Luthor
    -0.74
    EngineDebug
    -0.74
     è£ıè
    -0.70
    ãĤ¤
    -0.69
    ku
    -0.67
    hard
    -0.67
    tenance
    -0.65
    CVE
    -0.64
    POSITIVE LOGITS
    ategory
    1.62
    kefeller
    1.00
    elsius
    0.96
    ombat
    0.95
    avorite
    0.94
    uesday
    0.93
    urses
    0.91
    urrency
    0.90
    ycle
    0.90
    heed
    0.88
    Activations Density 0.010%

    No Known Activations