© 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. 1-RES-JB
    11. 20405
    Prev
    Next
    INDEX
    Explanations

    phrases related to the term "iq" and other variations of the word "iq" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the suffix "iq," "aq," or "uq" indicative of specific terminology related to culture or identity

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    channelAvailability
    -0.73
     Titanic
    -0.72
     Chrys
    -0.68
    ETA
    -0.67
     Nost
    -0.66
     ESA
    -0.62
     Apostles
    -0.61
     Vehicle
    -0.61
     CNS
    -0.61
     Principal
    -0.60
    POSITIVE LOGITS
    iq
    1.49
    inx
    0.97
    qa
    0.97
    abal
    0.91
    iang
    0.87
    hs
    0.87
    aq
    0.85
    ipedia
    0.84
    iencies
    0.84
    heed
    0.83
    Activations Density 0.005%

    No Known Activations