© 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. 1824
    Prev
    Next
    INDEX
    Explanations

    words related to the usage of resources or tools

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "utilize" and its variations

    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
    hood
    -0.74
    mad
    -0.72
    emb
    -0.70
    til
    -0.65
    brother
    -0.64
    mo
    -0.64
    nesty
    -0.63
    talk
    -0.62
    mortem
    -0.62
    occup
    -0.61
    POSITIVE LOGITS
     utilization
    0.91
     utilizes
    0.87
    prises
    0.87
    ments
    0.85
    iences
    0.81
    folios
    0.77
     util
    0.76
    edIn
    0.75
    nesday
    0.74
    FUL
    0.74
    Activations Density 0.038%

    No Known Activations