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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9473
    Prev
    Next
    INDEX
    Explanations

    adjectives related to being relaxed or not tightly fixed in place

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "loose" in various contexts

    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
    ãĤ´ãĥ³
    -0.71
    uyomi
    -0.69
    psey
    -0.68
    amus
    -0.67
    Reviewed
    -0.67
    oleon
    -0.66
     Nanto
    -0.66
    endix
    -0.66
    olan
    -0.66
    iterranean
    -0.66
    POSITIVE LOGITS
    leaf
    0.99
     loose
    0.86
    weed
    0.77
    bound
    0.76
    luster
    0.75
    cloth
    0.74
     coupling
    0.72
    wd
    0.72
    tail
    0.71
    nesses
    0.69
    Activations Density 0.006%

    No Known Activations