© 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. 3-RES-JB
    11. 12808
    Prev
    Next
    INDEX
    Explanations

    instances of the word "five"

    oai_token-act-pair · gpt-3.5-turbo

    the numeric representation of the word "five" and its occurrences in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ller
    -0.69
    hess
    -0.63
    DIT
    -0.62
     Happ
    -0.61
    iah
    -0.59
    Reviewer
    -0.59
    geist
    -0.59
    idence
    -0.58
    eus
    -0.58
    inated
    -0.57
    POSITIVE LOGITS
    teen
    1.41
    teenth
    1.36
    Thirty
    1.23
     hundred
    1.22
    eenth
    1.05
     months
    1.04
     thousand
    1.02
    aciously
    1.01
    acious
    0.97
     weeks
    0.97
    Activations Density 0.033%

    No Known Activations