© 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. 10-RES-JB
    11. 6323
    Prev
    Next
    INDEX
    Explanations

    pairs of names and their respective actions or positions

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals and their relationships in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ²¾
    -0.66
    Ļ½
    -0.66
    ©¶æ¥µ
    -0.64
    £ı
    -0.64
    CONCLUS
    -0.62
    cas
    -0.62
    Ī
    -0.62
    fortunately
    -0.61
    Parameter
    -0.61
     univers
    -0.60
    POSITIVE LOGITS
     pictured
    1.05
     flanked
    0.99
    window
    0.97
     poses
    0.85
     listens
    0.85
     Jr
    0.82
     photographed
    0.77
     wife
    0.77
     kisses
    0.77
     celebrates
    0.77
    Activations Density 0.116%

    No Known Activations