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. 11-RES-JB
    6. 15636
    Prev
    Next
    INDEX
    Explanations

    proper nouns of people related to technology and politics

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals or entities, particularly those with the initial 'J.'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Anthem
    -0.60
     Fas
    -0.58
     whistle
    -0.58
     Nunes
    -0.56
     foremost
    -0.56
     DRAG
    -0.53
    shed
    -0.52
     Camer
    -0.52
     arom
    -0.52
     torch
    -0.51
    POSITIVE LOGITS
    ilee
    0.97
    neys
    0.97
    usalem
    0.91
    iffe
    0.88
    ensen
    0.85
    unal
    0.78
    okia
    0.77
     Whedon
    0.76
    etus
    0.76
    ernaut
    0.75
    Activations Density 0.090%

    No Known Activations