© 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. 7-RES-JB
    11. 23469
    Prev
    Next
    INDEX
    Explanations

    mentions of the sports team "Watford"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Wat" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pmwiki
    -0.72
    Reviewer
    -0.69
    wcs
    -0.64
    interstitial
    -0.62
     Haas
    -0.62
    USE
    -0.60
     prevailing
    -0.60
     accounting
    -0.58
     blunt
    -0.58
     separatist
    -0.58
    POSITIVE LOGITS
    terson
    1.57
    chers
    1.19
    cher
    1.18
    ched
    1.10
    ches
    1.06
    combe
    1.06
    chens
    1.05
    chen
    1.04
    atche
    0.94
    pering
    0.93
    Activations Density 0.029%

    No Known Activations