© 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. 4301
    Prev
    Next
    INDEX
    Explanations

    phrases related to historical events and celebrations

    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
     disse
    -0.89
     seiz
    -0.78
     obser
    -0.72
     snail
    -0.71
     hemor
    -0.70
     Franch
    -0.66
    ãĥ¯ãĥ³
    -0.64
     antip
    -0.64
     dissemin
    -0.64
    icit
    -0.63
    POSITIVE LOGITS
    Ŀ
    1.77
    ¡
    1.40
    ľ
    1.15
    Ĵ
    1.15
    ¦
    1.12
    ª
    1.12
    Ĩ
    1.09
    Ķ
    1.08
    ©
    1.08
    ī
    1.07
    Activations Density 0.270%

    No Known Activations