© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 20501
    Prev
    Next
    INDEX
    Explanations

    phrases related to working with others on operations or projects to ensure accuracy and compliance

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to safety and security measures

    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
    famous
    -0.78
    Born
    -0.77
    ampire
    -0.73
    hung
    -0.72
    minus
    -0.71
     Economist
    -0.71
    pired
    -0.70
    lesi
    -0.65
    bare
    -0.65
    pill
    -0.65
    POSITIVE LOGITS
     feasibility
    1.12
     appropriate
    1.12
     compliance
    0.95
     feasible
    0.94
     lia
    0.92
     safeguards
    0.91
     contingency
    0.91
     exped
    0.90
     inquiries
    0.87
     refunds
    0.86
    Activations Density 0.647%

    No Known Activations