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. 10-RES-JB
    6. 22095
    Prev
    Next
    INDEX
    Explanations

    phrases related to global significance or excellence

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to "world-class" or globally recognized entities and qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    veyard
    -0.89
    edin
    -0.75
    ippi
    -0.74
    sbm
    -0.72
    cknowled
    -0.71
    ividual
    -0.71
    »Ĵ
    -0.69
     Mn
    -0.67
    Supplement
    -0.66
    hift
    -0.65
    POSITIVE LOGITS
     renown
    1.12
     renowned
    1.11
    wide
    1.03
     premiere
    1.00
     domination
    0.91
    liness
    0.91
    famous
    0.88
     famous
    0.88
     championships
    0.86
     champion
    0.85
    Activations Density 0.058%

    No Known Activations