© 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. 20917
    Prev
    Next
    INDEX
    Explanations

    proper nouns or words that begin with "col"

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "color."

    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
    WARE
    -0.74
    ELF
    -0.71
    ARP
    -0.71
    wered
    -0.70
    plug
    -0.70
    CVE
    -0.68
    visor
    -0.64
    butt
    -0.63
     Gingrich
    -0.63
    SEE
    -0.63
    POSITIVE LOGITS
    onel
    1.14
    ossal
    1.01
    ossus
    0.99
    umbo
    0.97
    ombo
    0.96
    onial
    0.95
    lections
    0.94
    oured
    0.91
    ouri
    0.90
    icol
    0.90
    Activations Density 0.008%

    No Known Activations