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. 0-RES-JB
    6. 4688
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Albert" with high relevance and strength

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Albert"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     SUP
    -0.69
    RPG
    -0.65
    entimes
    -0.64
     resize
    -0.64
     tether
    -0.63
    wcs
    -0.62
     ashore
    -0.61
    LCS
    -0.61
     XD
    -0.61
    offs
    -0.61
    POSITIVE LOGITS
     Albert
    3.76
    Albert
    2.88
     Alberta
    1.46
     Alfred
    1.32
     Einstein
    1.28
     Georg
    1.21
     Edmonton
    1.17
     Friedrich
    1.15
     Edmund
    1.15
     Ernest
    1.14
    Activations Density 0.013%

    No Known Activations