© 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. 13695
    Prev
    Next
    INDEX
    Explanations

    phrases indicating comparison or cause and effect

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating increasing quantities or magnitude

    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
    istani
    -0.87
    ahime
    -0.79
    ioch
    -0.76
    edit
    -0.73
    aido
    -0.71
    iasco
    -0.70
    lease
    -0.70
    idon
    -0.69
    opol
    -0.69
    amon
    -0.68
    POSITIVE LOGITS
     better
    1.46
     harder
    1.45
     worse
    1.39
     stronger
    1.39
     louder
    1.36
     clearer
    1.35
     quicker
    1.32
     greater
    1.32
     easier
    1.31
     happier
    1.30
    Activations Density 0.029%

    No Known Activations