© 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. 0-RES-JB
    11. 5287
    Prev
    Next
    INDEX
    Explanations

    the word "wrench" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "rench" and related terms

    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
     dod
    -0.79
     Bod
    -0.69
     Satoshi
    -0.68
     obtained
    -0.66
     stat
    -0.65
     avatar
    -0.62
     pseud
    -0.62
     Fib
    -0.61
     copies
    -0.61
     ancestor
    -0.60
    POSITIVE LOGITS
    rench
    4.46
    renches
    2.81
    renched
    1.92
     trench
    1.23
    raining
    0.98
     wrench
    0.95
    rain
    0.91
    raine
    0.90
    ür
    0.90
    rieg
    0.90
    Activations Density 0.018%

    No Known Activations