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. 11-RES-JB
    6. 20085
    Prev
    Next
    INDEX
    Explanations

    open-ended questions

    oai_token-act-pair · gpt-3.5-turbo

    questions that start with "What."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĹĺ
    -0.78
    forth
    -0.76
    ulic
    -0.65
    opes
    -0.63
    umber
    -0.63
    hide
    -0.62
    eer
    -0.62
    Null
    -0.61
    unin
    -0.61
     è£ıè¦ļéĨĴ
    -0.61
    POSITIVE LOGITS
     inspires
    1.06
     inspired
    1.03
     did
    0.99
     motiv
    0.95
     drove
    0.94
     motivated
    0.93
     drew
    0.91
     do
    0.91
     prompted
    0.88
     impressed
    0.87
    Activations Density 0.072%

    No Known Activations