© 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. 11-RES-JB
    11. 22440
    Prev
    Next
    INDEX
    Explanations

    mentions of sports clubs

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Club" that refer to various organizations or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¦
    -0.61
    PUT
    -0.61
     PLA
    -0.61
    ãģį
    -0.60
    NESS
    -0.57
    TPS
    -0.57
    Accessory
    -0.56
    ALLY
    -0.56
    ãģĹ
    -0.56
    alez
    -0.56
    POSITIVE LOGITS
    bers
    1.33
    bing
    1.30
    bable
    1.11
    bish
    1.05
    houses
    1.02
    bies
    0.96
    bed
    0.94
    ber
    0.94
    mers
    0.89
    imore
    0.87
    Activations Density 0.035%

    No Known Activations