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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4898
    Prev
    Next
    INDEX
    Explanations

    nationalities, geographical locations, and possibly ethnicities

    oai_token-act-pair · gpt-3.5-turbo

    references to specific nationalities or ethnic groups

    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
     chambers
    -0.69
     STATS
    -0.68
     guidance
    -0.65
    VERTIS
    -0.65
    theless
    -0.64
     incarn
    -0.63
     shroud
    -0.62
     interchange
    -0.62
     Gemini
    -0.62
     briefing
    -0.62
    POSITIVE LOGITS
    ians
    1.45
    ian
    1.10
    itives
    1.05
    riots
    1.01
    adian
    1.01
    arians
    1.00
    istani
    1.00
    ican
    0.98
    ants
    0.97
    inite
    0.97
    Activations Density 0.084%

    No Known Activations