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. 9116
    Prev
    Next
    INDEX
    Explanations

    mentions of specific locations or businesses, possibly related to financial or business dealings

    oai_token-act-pair · gpt-3.5-turbo

    the presence of a specific term or keyword

    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
     Parenthood
    -0.78
    terday
    -0.73
    ignty
    -0.66
     sclerosis
    -0.65
    theless
    -0.63
     nomine
    -0.61
    pher
    -0.60
    kHz
    -0.60
    birth
    -0.59
    CLASSIFIED
    -0.59
    POSITIVE LOGITS
    reement
    1.11
    gers
    1.09
    allery
    1.04
    hetto
    1.01
    azine
    1.01
    roup
    1.01
    glers
    1.01
    reements
    1.00
    ogo
    0.99
    lia
    0.98
    Activations Density 0.040%

    No Known Activations