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. 7-RES-JB
    6. 12776
    Prev
    Next
    INDEX
    Explanations

    safety instructions for preventing injuries in various scenarios

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to safety and injury prevention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ploma
    -0.72
    CEO
    -0.70
    icent
    -0.69
     outsourcing
    -0.69
    ellen
    -0.68
     Kaplan
    -0.67
     Lyndon
    -0.67
    empl
    -0.67
    Job
    -0.66
    chart
    -0.66
    POSITIVE LOGITS
     contaminants
    1.12
     contam
    1.01
     improperly
    0.99
     contamin
    0.99
     tresp
    0.97
     unprotected
    0.96
     intruder
    0.95
     surfaces
    0.94
     hazards
    0.94
     inflamm
    0.94
    Activations Density 0.705%

    No Known Activations