© 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. 8-RES-JB
    11. 13056
    Prev
    Next
    INDEX
    Explanations

    terms related to increases, such as "increased availability" and "rising demand."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to increases or rises in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    cients
    -0.68
     Cannes
    -0.66
     quir
    -0.63
     Mat
    -0.63
     entirety
    -0.62
     slightest
    -0.62
    igl
    -0.57
     Mans
    -0.57
     unnamed
    -0.56
    apest
    -0.56
    POSITIVE LOGITS
    than
    0.77
    ensity
    0.75
    ahime
    0.70
    catentry
    0.70
     intakes
    0.67
     Opportun
    0.67
     burdens
    0.66
    osph
    0.66
     levels
    0.65
     opportunities
    0.64
    Activations Density 0.287%

    No Known Activations