© 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. 10195
    Prev
    Next
    INDEX
    Explanations

    words related to providing food or services for an event or group

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "cater" and its variations

    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
    âĵĺ
    -0.99
    76561
    -0.86
     Scotia
    -0.78
    $$$$
    -0.74
    Export
    -0.73
    Hig
    -0.70
    Rum
    -0.70
    Rated
    -0.70
     Fein
    -0.69
    Es
    -0.68
    POSITIVE LOGITS
    pillar
    1.64
     cater
    1.46
    pill
    1.17
    xual
    1.08
     Cater
    1.03
    atered
    0.97
     catering
    0.93
    itionally
    0.91
    emaker
    0.90
    itect
    0.85
    Activations Density 0.005%

    No Known Activations