© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 12223
    Prev
    Next
    INDEX
    Explanations

    words related to providing food or services, especially catering specifically

    oai_token-act-pair · gpt-3.5-turbo

    the word "cater" and its variations in different contexts

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

    No Comments

    Negative Logits
     Scotia
    -0.93
     Jericho
    -0.72
     Apostles
    -0.71
     Rasmussen
    -0.69
     Fein
    -0.68
    $$$$
    -0.67
    Es
    -0.67
    âĵĺ
    -0.67
     Snowden
    -0.66
     Dead
    -0.63
    POSITIVE LOGITS
    pillar
    1.73
    pill
    1.21
     cater
    1.20
    xual
    1.00
    itionally
    0.98
    efully
    0.92
    itect
    0.88
     catering
    0.86
    atered
    0.86
    alore
    0.86
    Activations Density 0.009%

    No Known Activations