© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 23235
    Prev
    Next
    INDEX
    Explanations

    instances of the word "hey"

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "hey" and related expressions in a conversational context

    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
    arium
    -0.69
    RAW
    -0.68
     Biol
    -0.67
     Destroyer
    -0.65
    ب
    -0.65
     submarines
    -0.65
     understatement
    -0.64
     Vessel
    -0.62
    Bound
    -0.62
     logical
    -0.60
    POSITIVE LOGITS
    hey
    1.59
    bye
    0.90
    orkshire
    0.84
    boys
    0.84
    terness
    0.83
    pants
    0.83
    tons
    0.82
    mond
    0.82
    oga
    0.82
    cott
    0.82
    Activations Density 0.004%

    No Known Activations