© 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. 24396
    Prev
    Next
    INDEX
    Explanations

    words related to political activities or situations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 'f'

    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
     machine
    -0.68
     bacter
    -0.61
     plural
    -0.60
     Leopard
    -0.59
    NESS
    -0.59
     paraly
    -0.58
    manship
    -0.58
     overflow
    -0.57
    face
    -0.57
     Esports
    -0.57
    POSITIVE LOGITS
    iddling
    1.45
    MRI
    1.35
    idget
    1.34
    ussy
    1.31
    athom
    1.29
    iddle
    1.28
    enced
    1.27
    iddler
    1.26
    iesta
    1.23
    auc
    1.22
    Activations Density 0.023%

    No Known Activations