© 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. 11431
    Prev
    Next
    INDEX
    Explanations

    specific text characters, likely related to a particular language or encoding

    oai_token-act-pair · gpt-3.5-turbo

    specific hyphenated words or terms related to political 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
     Zot
    -0.64
     Admir
    -0.64
    Introduced
    -0.63
     Brill
    -0.63
     Cruiser
    -0.62
     trumpet
    -0.59
     Breath
    -0.59
     Booker
    -0.58
     cart
    -0.56
    Newsletter
    -0.55
    POSITIVE LOGITS
    etry
    0.79
    opian
    0.78
    agog
    0.77
    opic
    0.77
    itary
    0.72
    ampton
    0.71
    ét
    0.69
    ogn
    0.69
    oki
    0.68
    cially
    0.68
    Activations Density 0.119%

    No Known Activations