© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 22617
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to a specific location or brand

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns related to places and people

    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
    20439
    -0.91
    interstitial
    -0.76
    BUG
    -0.70
    NBA
    -0.69
    \",
    -0.65
    roxy
    -0.64
    wolves
    -0.64
    éĹĺ
    -0.62
    uggets
    -0.62
     concussion
    -0.61
    POSITIVE LOGITS
     Kash
    3.59
     Tat
    2.06
     Shan
    1.30
     Kyr
    0.97
     Tiff
    0.93
    avin
    0.92
     Poverty
    0.92
     Ai
    0.91
     Wor
    0.86
     Nare
    0.86
    Activations Density 0.029%

    No Known Activations