© 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. 0-RES-JB
    11. 18261
    Prev
    Next
    INDEX
    Explanations

    mentions of actions or events that need a consensual agreement

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "ate."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    saf
    -0.67
     wards
    -0.67
     inspir
    -0.64
     Marsh
    -0.62
     guarding
    -0.62
     sickness
    -0.61
     Frey
    -0.61
     Ill
    -0.60
     hair
    -0.60
     dem
    -0.60
    POSITIVE LOGITS
    ATE
    4.10
    ATES
    2.99
    ATED
    2.42
    ATING
    2.30
    ate
    2.17
    ates
    2.02
    ATOR
    1.88
    ACY
    1.87
    ATION
    1.75
    ATIVE
    1.74
    Activations Density 0.008%

    No Known Activations