© 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. 2-RES-JB
    11. 23975
    Prev
    Next
    INDEX
    Explanations

    words that emphasize a high degree or intensity of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the word "practically" 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 @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    Gate
    -0.73
    will
    -0.72
     Cly
    -0.72
    rive
    -0.69
    agate
    -0.68
    immer
    -0.66
    IDA
    -0.66
     Gate
    -0.65
    sche
    -0.65
    apego
    -0.64
    POSITIVE LOGITS
    thood
    0.83
     illiter
    0.74
     indistinguishable
    0.70
    ãĤ§
    0.70
     unint
    0.67
    ength
    0.67
    ©¶æ¥µ
    0.66
     unus
    0.66
    rency
    0.66
     unemploy
    0.66
    Activations Density 0.003%

    No Known Activations