© 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. 0-RES-JB
    11. 7527
    Prev
    Next
    INDEX
    Explanations

    instances of the word "counted" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "counted" and its variations

    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
     Upton
    -0.66
     environment
    -0.64
    ennes
    -0.63
    Insp
    -0.63
     environments
    -0.63
    erson
    -0.62
    endon
    -0.62
    ienne
    -0.60
     appliance
    -0.57
     Osc
    -0.57
    POSITIVE LOGITS
     counted
    3.83
     count
    2.23
     counts
    2.11
     tallied
    1.97
     counting
    1.89
     reckoned
    1.68
    count
    1.62
     accounted
    1.43
     Count
    1.39
     numbered
    1.30
    Activations Density 0.009%

    No Known Activations