© 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. 9-RES-JB
    11. 20875
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Dal" followed by various letters or numbers

    oai_token-act-pair · gpt-3.5-turbo

    the specific term "Dal 2" within the text

    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
    sburgh
    -0.72
    aceous
    -0.69
     Lovecraft
    -0.67
    ItemTracker
    -0.63
    hift
    -0.61
     Parenthood
    -0.60
     Collider
    -0.59
     Canterbury
    -0.57
     unanimous
    -0.57
     actionGroup
    -0.56
    POSITIVE LOGITS
    inar
    0.90
    vik
    0.90
    pling
    0.86
    rolet
    0.84
    oris
    0.82
    aran
    0.81
    quer
    0.80
    uci
    0.80
    iber
    0.80
    jan
    0.79
    Activations Density 0.043%

    No Known Activations