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. 0-RES-JB
    6. 4618
    Prev
    Next
    INDEX
    Explanations

    groups of diverse populations or communities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to different ethnic and indigenous groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ection
    -0.78
    ector
    -0.76
     Radar
    -0.67
    trap
    -0.66
    Correction
    -0.61
    utton
    -0.60
     Machine
    -0.60
    Required
    -0.60
    ctor
    -0.60
     Cure
    -0.59
    POSITIVE LOGITS
     peoples
    3.43
     Peoples
    1.80
    oples
    1.50
     civilizations
    1.37
     nations
    1.36
     cultures
    1.33
     populations
    1.30
     societies
    1.26
     tribes
    1.18
     inhabitants
    1.16
    Activations Density 0.011%

    No Known Activations