© 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. 4-RES-JB
    11. 17265
    Prev
    Next
    INDEX
    Explanations

    instances of the letters and syllables associated with the name "Tim" and its variations

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

    phrases related to the person "Tim"

    oai_token-act-pair · gpt-3.5-turbo
    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
    ccording
    -0.77
    ername
    -0.76
    #$#$
    -0.75
    taboola
    -0.73
    INC
    -0.72
    CHA
    -0.69
     Bonds
    -0.68
     pestic
    -0.68
    ModLoader
    -0.68
    TAIN
    -0.67
    POSITIVE LOGITS
    opol
    0.77
    gow
    0.76
    iday
    0.74
    çīĪ
    0.72
    aida
    0.71
    umatic
    0.71
    mond
    0.69
    kson
    0.66
    naires
    0.65
    udic
    0.65
    Activations Density 0.251%

    No Known Activations