© 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. 9-RES-JB
    6. 5861
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "to."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    options or commands in a selection menu or interface

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    distance
    -0.60
    hens
    -0.57
     Supervisor
    -0.56
    igslist
    -0.56
    wagon
    -0.54
    ccording
    -0.53
    abase
    -0.53
     conced
    -0.52
    FTWARE
    -0.52
     Luffy
    -0.52
    POSITIVE LOGITS
     subscribe
    0.79
     refresh
    0.75
     enable
    0.74
    register
    0.74
     navigate
    0.73
     keep
    0.71
     receive
    0.70
     activate
    0.69
    lect
    0.69
     fill
    0.69
    Activations Density 0.032%

    No Known Activations