© 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. 9284
    Prev
    Next
    INDEX
    Explanations

    the word "myriad" or related words denoting a large number or variety

    oai_token-act-pair · gpt-3.5-turbo

    terms indicating a large number or variety of items

    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
    ishops
    -0.77
    sein
    -0.75
    WAR
    -0.73
    atche
    -0.71
    estamp
    -0.70
    ablishment
    -0.70
    inates
    -0.68
    istine
    -0.68
    _-
    -0.67
    abad
    -0.66
    POSITIVE LOGITS
     array
    0.82
    ãĥ¼ãĥĨãĤ£
    0.82
     Ways
    0.78
    entimes
    0.78
    ãĥĥãĤ¯
    0.76
     myriad
    0.74
    urst
    0.74
     facets
    0.73
     aspects
    0.72
    ĸļ
    0.71
    Activations Density 0.007%

    No Known Activations