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. 6-RES-JB
    6. 21174
    Prev
    Next
    INDEX
    Explanations

    common male names or abbreviations containing the letter "d" followed by a vowel

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of people and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Vinyl
    -0.72
    yip
    -0.69
     HDL
    -0.62
    verty
    -0.61
     Dragonbound
    -0.58
     warranted
    -0.56
    çͰ
    -0.56
     Mahjong
    -0.56
    itives
    -0.55
    iday
    -0.54
    POSITIVE LOGITS
    alion
    0.80
    ciating
    0.78
    rency
    0.72
    igm
    0.72
    amation
    0.67
    idated
    0.66
    icio
    0.66
    liction
    0.65
    pora
    0.64
    agram
    0.64
    Activations Density 0.072%

    No Known Activations