© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 15296
    Prev
    Next
    INDEX
    Explanations

    words related to dining or eating

    oai_token-act-pair · gpt-3.5-turbo

    words related to dining and meals

    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
    ãĥŁ
    -0.74
    JV
    -0.72
    SpaceEngineers
    -0.70
    qqa
    -0.65
    ocument
    -0.63
    imov
    -0.63
    LM
    -0.63
     Territories
    -0.62
     ç¥ŀ
    -0.62
     Gree
    -0.61
    POSITIVE LOGITS
    bags
    0.88
    rences
    0.79
    bag
    0.77
    illet
    0.76
    hower
    0.76
    ennes
    0.75
     Restaur
    0.74
    goers
    0.70
    mort
    0.69
    eteria
    0.67
    Activations Density 0.053%

    No Known Activations