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. 7-RES-JB
    6. 901
    Prev
    Next
    INDEX
    Explanations

    proper names 'Jason'

    oai_token-act-pair · gpt-3.5-turbo

    the name "Jason" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ship
    -0.95
    recomm
    -0.82
    itionally
    -0.77
    Reviewer
    -0.74
    Ñĭ
    -0.73
    lucent
    -0.73
    iments
    -0.73
    sheets
    -0.72
    dayName
    -0.71
    gra
    -0.71
    POSITIVE LOGITS
     Bour
    0.90
     Aaron
    0.85
     Lev
    0.83
     Kidd
    0.79
     Kessler
    0.79
     Wright
    0.78
     Hanson
    0.78
     Alexander
    0.78
     Chaff
    0.78
     Garrett
    0.77
    Activations Density 0.023%

    No Known Activations