Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 12285
    Prev
    Next
    INDEX
    Explanations

    the letter 'k' followed by a number indicating severity or strength

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter "k"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •words starting with k

    No Comments

    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -0.82
    éĹĺ
    -0.81
    ãĥ¯
    -0.77
    byter
    -0.77
    ãĥ´ãĤ¡
    -0.72
    ÙIJ
    -0.71
    */(
    -0.70
    terday
    -0.70
    IBLE
    -0.69
    hedon
    -0.69
    POSITIVE LOGITS
    ratom
    1.06
    etchup
    1.02
    rieg
    0.99
    itty
    0.96
    won
    0.91
    idd
    0.90
    erning
    0.87
    appa
    0.86
    ansas
    0.85
    uk
    0.85
    Activations Density 0.011%

    No Known Activations