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. 16099
    Prev
    Next
    INDEX
    Explanations

    positive and forward-looking statements related to progress and achievement

    oai_token-act-pair · gpt-3.5-turbo

    significant achievements or milestones related to investments and economic progress

    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
     disappro
    -0.80
     offending
    -0.79
     ridicule
    -0.79
     woes
    -0.78
    ulner
    -0.76
     insults
    -0.75
    Invalid
    -0.75
     banned
    -0.74
     errone
    -0.74
     brut
    -0.74
    POSITIVE LOGITS
     collaborative
    1.19
     opportunity
    1.15
     partnership
    1.11
     collaboration
    1.10
     culmination
    1.02
     synergy
    1.00
     catalyst
    0.99
     initiative
    0.96
     seamless
    0.95
     complementary
    0.92
    Activations Density 0.339%

    No Known Activations