© 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. 1-RES-JB
    11. 3873
    Prev
    Next
    INDEX
    Explanations

    references to a specific location or entity named "Beaver Island"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations and entities, particularly "Beaver."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nesota
    -1.01
    isphere
    -0.89
    uana
    -0.84
    aps
    -0.83
    eport
    -0.83
    iaries
    -0.82
    eth
    -0.82
    eland
    -0.80
    eways
    -0.80
    pez
    -0.79
    POSITIVE LOGITS
     Beaver
    0.89
     Beetle
    0.86
     Penguin
    0.85
     Haram
    0.83
     Kush
    0.78
    jar
    0.76
     Magnum
    0.76
     Faw
    0.75
     Squid
    0.74
     volleyball
    0.74
    Activations Density 0.030%

    No Known Activations