© 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. 7-RES-JB
    11. 22913
    Prev
    Next
    INDEX
    Explanations

    specific instances of things being utilized or operated by someone

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate methods or processes involving the word "using."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hood
    -0.75
    naire
    -0.74
     greets
    -0.73
    uberty
    -0.72
    hound
    -0.72
    merce
    -0.71
     accompanies
    -0.70
    nesty
    -0.69
    sylv
    -0.68
    owship
    -0.68
    POSITIVE LOGITS
     methods
    0.78
    FUL
    0.77
     techniques
    0.77
    fully
    0.74
    BUS
    0.72
     scissors
    0.71
     inputs
    0.70
     coupons
    0.69
     ropes
    0.69
     computers
    0.69
    Activations Density 0.055%

    No Known Activations