© 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. 3-RES-JB
    11. 1779
    Prev
    Next
    INDEX
    Explanations

    instances where the word "including" is used

    oai_token-act-pair · gpt-3.5-turbo

    the word "including" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    acia
    -0.74
    cia
    -0.74
    vous
    -0.73
    opy
    -0.71
    osta
    -0.67
    ython
    -0.66
    gged
    -0.66
    itudes
    -0.65
    ollo
    -0.65
    dayName
    -0.64
    POSITIVE LOGITS
    ãĤ½
    0.72
    :,
    0.70
     Accessories
    0.68
    :(
    0.67
     Include
    0.66
    ãĥ¯ãĥ³
    0.63
    itarian
    0.63
    ãĤ´
    0.63
    mast
    0.62
    :-
    0.62
    Activations Density 0.057%

    No Known Activations