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. 4-RES-JB
    6. 18158
    Prev
    Next
    INDEX
    Explanations

    phrases concerning specific groups of people

    oai_token-act-pair · gpt-3.5-turbo

    references to specific groups or individuals in discussions of social or political issues

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

    No Comments

    Negative Logits
    onis
    -0.73
    ILY
    -0.71
     Minion
    -0.69
     Resolution
    -0.67
    ob
    -0.67
    Luck
    -0.65
    ointment
    -0.65
    âĺħâĺħ
    -0.65
    eling
    -0.64
    enegger
    -0.64
    POSITIVE LOGITS
     kinds
    0.94
     sorts
    0.86
     pesky
    0.80
     favoring
    0.75
     surveyed
    0.73
     wishing
    0.73
     interested
    0.73
     attending
    0.73
     aspects
    0.71
     redes
    0.70
    Activations Density 0.068%

    No Known Activations