© 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. 9-RES-JB
    11. 10102
    Prev
    Next
    INDEX
    Explanations

    instances of the word "noticed."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "notice" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uries
    -0.86
    ibur
    -0.71
    displayText
    -0.69
    orthy
    -0.68
    iah
    -0.66
    ommod
    -0.65
    ogens
    -0.64
     reckoning
    -0.64
    etimes
    -0.64
    quished
    -0.64
    POSITIVE LOGITS
     similarity
    0.95
     inconsistency
    0.95
     strangely
    0.94
     similarities
    0.93
     oddly
    0.89
     inconsistencies
    0.84
     resemblance
    0.83
     curiously
    0.81
     lately
    0.81
     trend
    0.80
    Activations Density 0.310%

    No Known Activations