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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 8-RES-JB
    6. 18647
    Prev
    Next
    INDEX
    Explanations

    minerals and chemical elements

    oai_token-act-pair · gpt-3.5-turbo

    chemical compounds and minerals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Privacy
    -0.89
     Intervention
    -0.88
     curfew
    -0.88
     Homeless
    -0.84
    HUD
    -0.83
    luck
    -0.78
    menu
    -0.77
    Kids
    -0.76
     attentive
    -0.76
     Menu
    -0.75
    POSITIVE LOGITS
     oxide
    1.51
     atoms
    1.42
     metals
    1.40
     minerals
    1.37
     crystals
    1.36
     alloy
    1.33
     particles
    1.31
     ammon
    1.30
    utonium
    1.30
     hydrogen
    1.27
    Activations Density 0.474%

    No Known Activations