Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 10477
    Prev
    Next
    INDEX
    Explanations

    phrases related to locations, organizations, and events associated with the term "Apostacon"

    oai_token-act-pair · gpt-3.5-turbo

    elements related to URLs and web addresses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abase
    -0.64
     Fargo
    -0.61
    ãĤ¹ãĥĪ
    -0.60
    trump
    -0.59
    Loop
    -0.58
    ãĤ¶
    -0.57
    Ping
    -0.56
    quez
    -0.55
     Dane
    -0.55
     ecology
    -0.55
    POSITIVE LOGITS
    monary
    0.87
    earances
    0.85
    aic
    0.80
    ogram
    0.74
    illus
    0.73
    irie
    0.73
    aea
    0.72
    rha
    0.71
    umatic
    0.71
    imately
    0.70
    Activations Density 0.145%

    No Known Activations