© 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. 15006
    Prev
    Next
    INDEX
    Explanations

    keywords related to the term "Wat" which might refer to "Watford"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Watford."

    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
    Reviewer
    -0.69
    Enlarge
    -0.68
     Volks
    -0.63
     prevailing
    -0.63
    ICT
    -0.62
     moons
    -0.61
     displ
    -0.61
     crush
    -0.60
     Barnett
    -0.59
     ASC
    -0.59
    POSITIVE LOGITS
    terson
    1.68
    chers
    1.36
    cher
    1.33
    kinson
    1.24
    ches
    1.23
    ched
    1.16
    auga
    1.13
    chen
    1.12
    atsuki
    1.08
    chens
    1.05
    Activations Density 0.040%

    No Known Activations