© 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. 9-RES-JB
    11. 10366
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific situation or the state of something

    oai_token-act-pair · gpt-3.5-turbo

    instances of negation and their associated implications in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ortment
    -0.70
    ancies
    -0.64
     occupancy
    -0.63
     wheelchair
    -0.59
    ricted
    -0.58
    apons
    -0.57
     likeness
    -0.56
    ilings
    -0.56
     utilization
    -0.56
    okingly
    -0.55
    POSITIVE LOGITS
    _.
    0.96
    .
    0.96
    \.
    0.91
     anyway
    0.91
    .</
    0.90
    .#
    0.90
    .*
    0.86
     :-)
    0.82
     anymore
    0.82
    .<
    0.82
    Activations Density 0.636%

    No Known Activations