© 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. 2-RES-JB
    11. 8150
    Prev
    Next
    INDEX
    Explanations

    instances of positive words or phrases

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HAEL
    -0.81
    æĸ¹
    -0.76
    ãģ®å®
    -0.72
    loo
    -0.70
    ORGE
    -0.68
     Mellon
    -0.67
    ESH
    -0.67
    AMES
    -0.66
    OME
    -0.66
    ONEY
    -0.65
    POSITIVE LOGITS
    itivity
    1.08
     pos
    1.06
    itional
    1.01
    pos
    0.99
    sembly
    0.94
    iton
    0.93
    fet
    0.93
    ited
    0.93
    idon
    0.92
    itory
    0.90
    Activations Density 0.012%

    No Known Activations