© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 23624
    Prev
    Next
    INDEX
    Explanations

    numerical measurements related to square area

    oai_token-act-pair · gpt-3.5-turbo

    terms related to square measurements and area

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     GOODMAN
    -0.92
     bearer
    -0.91
    child
    -0.74
     responsible
    -0.73
     Turing
    -0.72
    boards
    -0.72
     Johann
    -0.64
     Almighty
    -0.63
     Beckham
    -0.62
    fuck
    -0.62
    POSITIVE LOGITS
    inct
    0.85
    sq
    0.82
     sq
    0.79
    otal
    0.77
    atel
    0.76
    avin
    0.76
    q
    0.76
    obar
    0.75
    º
    0.74
    renheit
    0.72
    Activations Density 0.009%

    No Known Activations