© 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. 0-RES-JB
    6. 7829
    Prev
    Next
    INDEX
    Explanations

    the number "five"

    oai_token-act-pair · gpt-3.5-turbo

    references to the number five

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Discuss
    -0.72
    ãģ®å®
    -0.63
    ================================================================
    -0.63
    conom
    -0.59
    Creating
    -0.59
    !!!!!
    -0.59
    idia
    -0.58
    atche
    -0.57
     ðŁĻĤ
    -0.57
    needed
    -0.57
    POSITIVE LOGITS
     five
    2.79
     seven
    2.37
     six
    2.36
     four
    2.35
    five
    2.25
     three
    2.20
     nine
    2.17
     eight
    2.16
     fifteen
    2.04
     Five
    2.00
    Activations Density 0.023%

    No Known Activations