© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 10049
    Prev
    Next
    INDEX
    Explanations

    words related to making a formal announcement or declaration

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "called for."

    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
     ®
    -0.80
    edin
    -0.77
    fo
    -0.75
    æ³
    -0.71
    osterone
    -0.70
    é¾
    -0.70
    uded
    -0.69
    tch
    -0.68
    PI
    -0.67
    fleet
    -0.67
    POSITIVE LOGITS
     clarification
    1.08
     abol
    1.06
     reconsider
    1.05
     stricter
    1.03
     urgent
    0.98
     tighter
    0.98
     unity
    0.93
     speedy
    0.93
     drastic
    0.93
     reinforcements
    0.93
    Activations Density 0.081%

    No Known Activations