© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 20234
    Prev
    Next
    INDEX
    Explanations

    specific government positions and titles

    oai_token-act-pair · gpt-3.5-turbo

    references to ambassadors and diplomatic roles

    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
    ilogy
    -0.67
    entimes
    -0.67
     snowball
    -0.66
    empt
    -0.66
    atown
    -0.64
     Marketable
    -0.63
    angled
    -0.60
    castle
    -0.59
    arbon
    -0.58
    odes
    -0.58
    POSITIVE LOGITS
     Daniel
    1.59
     Jonathan
    1.58
     Patrick
    1.57
     David
    1.56
     Andrew
    1.54
     Kevin
    1.54
     Richard
    1.53
     Brian
    1.53
     Philippe
    1.52
     Joel
    1.52
    Activations Density 1.016%

    No Known Activations