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

    Neuronpedia

    Jacobian LensNEW
    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. 0-RES-JB
    11. 13572
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Low"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "Low" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prin
    -0.70
    actor
    -0.68
     anew
    -0.63
    agons
    -0.62
    ãĤ·ãĥ£
    -0.62
    arenthood
    -0.62
     versa
    -0.61
     branching
    -0.61
    xon
    -0.60
     alleg
    -0.59
    POSITIVE LOGITS
     Low
    3.47
    Low
    2.99
     LOW
    2.17
    low
    2.13
     Lowe
    1.90
     low
    1.76
     Lower
    1.67
     High
    1.58
     lows
    1.49
    Lower
    1.42
    Activations Density 0.009%

    No Known Activations