© 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. 2-RES-JB
    11. 13715
    Prev
    Next
    INDEX
    Explanations

    mentions of specific geographical locations, specifically islands like Barbuda and Barbados

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Barb" and its variations, particularly in the context of locations or cultural references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    train
    -0.94
    EVA
    -0.82
    EngineDebug
    -0.78
    æĸ¹
    -0.76
    lihood
    -0.75
    æĪ
    -0.74
    hower
    -0.74
    DER
    -0.72
    nder
    -0.71
    ffic
    -0.71
    POSITIVE LOGITS
    ados
    1.03
    ican
    1.02
    adian
    1.00
    arella
    0.93
    izon
    0.93
     Barb
    0.93
    adoes
    0.92
    abies
    0.90
    icans
    0.87
    uda
    0.85
    Activations Density 0.009%

    No Known Activations