© 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. 3-RES-JB
    11. 17192
    Prev
    Next
    INDEX
    Explanations

    referenes to the computing term "x86"

    oai_token-act-pair · gpt-3.5-turbo

    references to the x86 architecture and related technical specifications

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     compr
    -0.78
    itton
    -0.77
    */(
    -0.74
    vati
    -0.73
    usalem
    -0.70
    rison
    -0.67
    alez
    -0.65
    uden
    -0.65
    pressure
    -0.65
    printed
    -0.64
    POSITIVE LOGITS
    20439
    0.94
    âĶĢ
    0.87
    80
    0.76
    64
    0.75
    tenance
    0.73
    ±
    0.72
    016
    0.72
     Minutes
    0.71
    %:
    0.71
    rpm
    0.71
    Activations Density 0.027%

    No Known Activations