© 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. 11-RES-JB
    11. 1185
    Prev
    Next
    INDEX
    Explanations

    email addresses or website URLs

    oai_token-act-pair · gpt-3.5-turbo

    instances of the character '<|endoftext|>'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Nev
    -0.55
     opposite
    -0.54
     paving
    -0.53
     Ninth
    -0.53
     filling
    -0.51
     gearing
    -0.51
     encomp
    -0.50
     bearing
    -0.50
     widening
    -0.50
     fueling
    -0.49
    POSITIVE LOGITS
    maxwell
    0.99
    duino
    0.78
    irez
    0.76
    fml
    0.75
    ntax
    0.74
    jac
    0.73
    redits
    0.73
    _
    0.72
    xc
    0.71
    amel
    0.71
    Activations Density 0.157%

    No Known Activations