© 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. 9-RES-JB
    11. 4321
    Prev
    Next
    INDEX
    Explanations

    names or terms related to a specific person, "Lub"

    oai_token-act-pair · gpt-3.5-turbo
    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
    è»
    -0.78
     Mount
    -0.77
     Territories
    -0.71
     bookmark
    -0.69
    Gra
    -0.69
     Kinder
    -0.67
     Gaw
    -0.67
     mount
    -0.67
     polic
    -0.66
     Warfare
    -0.66
    POSITIVE LOGITS
    in
    1.51
    ins
    1.48
    inian
    1.43
    ino
    1.40
    IN
    1.37
    ini
    1.32
    ÃŃn
    1.30
    inis
    1.30
    inos
    1.24
    inia
    1.22
    Activations Density 0.140%

    No Known Activations