© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 13013
    Prev
    Next
    INDEX
    Explanations

    abstract or technical terms related to various fields such as medicine, technology, infrastructure, and government

    oai_token-act-pair · gpt-3.5-turbo

    terms related to infrastructure and organizational issues

    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
    âĢ
    -0.80
     ÂŃ
    -0.72
    etheless
    -0.70
    ãĥĥãĥī
    -0.68
    .—
    -0.67
    ÂŃ
    -0.66
    +.
    -0.66
    .''
    -0.66
    prep
    -0.66
    )—
    -0.64
    POSITIVE LOGITS
     amongst
    0.88
     regarding
    0.86
     towards
    0.85
     etc
    0.84
     of
    0.79
     concerning
    0.75
     for
    0.73
     whilst
    0.70
     relating
    0.70
     thru
    0.69
    Activations Density 0.886%

    No Known Activations