© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 22755
    Prev
    Next
    INDEX
    Explanations

    numbers being counted

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "counting" in various contexts

    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
    ought
    -0.65
    tek
    -0.63
    irt
    -0.63
    )=(
    -0.63
    aft
    -0.61
    ————————————————
    -0.61
    anse
    -0.60
    iste
    -0.60
    KEN
    -0.60
    isite
    -0.59
    POSITIVE LOGITS
     counting
    4.06
     count
    1.98
     counted
    1.87
     counts
    1.68
    count
    1.48
     tally
    1.40
     numbering
    1.38
     Count
    1.36
     calculating
    1.28
    Count
    1.27
    Activations Density 0.006%

    No Known Activations