© 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. 12733
    Prev
    Next
    INDEX
    Explanations

    economic and statistical information and comparison

    oai_token-act-pair · gpt-3.5-turbo

    quantifiable statements about resource allocation and consumption

    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
    IJ
    -0.66
    vier
    -0.65
    LER
    -0.61
     thous
    -0.59
    ¯¯
    -0.59
    miah
    -0.58
     Ranking
    -0.58
    otiation
    -0.57
    oti
    -0.57
    most
    -0.57
    POSITIVE LOGITS
     attributable
    1.07
     devoted
    1.06
     attributed
    0.88
     concentrated
    0.86
     comprised
    0.86
     reserved
    0.84
     gone
    0.83
    awaru
    0.83
     derived
    0.82
     dedicated
    0.81
    Activations Density 0.165%

    No Known Activations