© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 11-RES-JB
    11. 14791
    Prev
    Next
    INDEX
    Explanations

    phrases related to conjuring or configuring something

    oai_token-act-pair · gpt-3.5-turbo

    words related to creating or configuring something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wynne
    -0.70
     Sisters
    -0.70
     Leone
    -0.64
    FORE
    -0.62
     Fallon
    -0.61
     boarding
    -0.61
     Flan
    -0.58
    clinton
    -0.58
     Quinn
    -0.57
     butt
    -0.57
    POSITIVE LOGITS
    ured
    2.62
    ure
    2.55
    ures
    2.55
    uring
    2.50
    urers
    2.35
    urer
    2.35
    uration
    2.00
    URES
    1.99
    URE
    1.98
    urations
    1.97
    Activations Density 0.093%

    No Known Activations