Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11127
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter "U" followed by a single-digit number

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the letter "U" followed by a number, indicating references to a university or similar institution

    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
     Noir
    -0.77
     CPC
    -0.65
     hust
    -0.65
     CDs
    -0.65
     Preferred
    -0.64
     proceeds
    -0.62
     ashore
    -0.62
     Metatron
    -0.62
     jams
    -0.61
     bottleneck
    -0.60
    POSITIVE LOGITS
    prising
    1.34
    seless
    1.18
    nexpected
    1.17
    lyss
    1.10
    PDATED
    1.05
    gly
    1.04
    topia
    1.03
    NA
    1.01
    pperc
    0.99
    DP
    0.97
    Activations Density 0.059%

    No Known Activations