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. 4-RES-JB
    6. 8239
    Prev
    Next
    INDEX
    Explanations

    words containing the sequence "oo" with a high activation value

    oai_token-act-pair · gpt-3.5-turbo

    instances of the vowel sound 'oo'

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

    No Comments

    Negative Logits
    代
    -0.87
     misunder
    -0.73
    DonaldTrump
    -0.69
    ÑĮ
    -0.69
     conduc
    -0.68
    Downloadha
    -0.67
    nces
    -0.66
    imir
    -0.66
     distingu
    -0.66
    idates
    -0.65
    POSITIVE LOGITS
    oos
    1.16
    leans
    1.04
    gee
    1.00
    lean
    0.94
    oot
    0.94
    zee
    0.93
    oop
    0.91
    gey
    0.90
    zing
    0.89
    ffic
    0.89
    Activations Density 0.012%

    No Known Activations