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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 2372
    Prev
    Next
    INDEX
    Explanations

    words related to technology and actions taken or not taken in a specific context

    oai_token-act-pair · gpt-3.5-turbo

    instances of actions or events that indicate failure or error

    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
     suspic
    -0.56
    views
    -0.51
    WORK
    -0.51
    earned
    -0.49
     Hammond
    -0.49
    forts
    -0.49
    ISTORY
    -0.48
    redits
    -0.48
    interstitial
    -0.48
     prejudice
    -0.47
    POSITIVE LOGITS
     Leilan
    0.83
    soDeliveryDate
    0.62
     [|
    0.58
     pandemonium
    0.57
     Marketable
    0.56
     Cthulhu
    0.54
    ãĥīãĥ©ãĤ´ãĥ³
    0.54
     Seraph
    0.53
     Andromeda
    0.52
     Neptune
    0.51
    Activations Density 1.516%

    No Known Activations