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. 4-RES-JB
    6. 23537
    Prev
    Next
    INDEX
    Explanations

    names related to European or Russian political figures

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names and locations

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

    No Comments

    Negative Logits
    eed
    -0.77
    ree
    -0.72
    ById
    -0.71
     Cind
    -0.69
    Quantity
    -0.69
     Debor
    -0.67
     Thumbnails
    -0.67
    س
    -0.66
    ered
    -0.65
    inator
    -0.65
    POSITIVE LOGITS
    vironment
    0.98
    umbers
    0.93
    nen
    0.91
    ners
    0.90
    onen
    0.88
    atsu
    0.86
    ipple
    0.85
    stra
    0.82
    strument
    0.82
    ervative
    0.81
    Activations Density 0.024%

    No Known Activations