© 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. 4906
    Prev
    Next
    INDEX
    Explanations

    verbs related to tracking or finding someone or something

    oai_token-act-pair · gpt-3.5-turbo

    the word "tracked" and its variations, indicating a focus on monitoring or following events or subjects

    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
    itone
    -0.76
     Opening
    -0.72
    imum
    -0.70
    itation
    -0.69
    begin
    -0.64
    prep
    -0.63
     appropri
    -0.63
    itta
    -0.62
     unity
    -0.62
    gen
    -0.62
    POSITIVE LOGITS
     tracked
    3.77
     traced
    1.86
     monitored
    1.84
     analyzed
    1.47
     hunted
    1.45
     analysed
    1.44
     track
    1.40
     mapped
    1.36
     tracks
    1.35
     detected
    1.34
    Activations Density 0.013%

    No Known Activations