© 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. 4-RES-JB
    11. 14739
    Prev
    Next
    INDEX
    Explanations

    names of politicians or public figures

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names of individuals

    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
    ational
    -0.84
    utation
    -0.79
    Magikarp
    -0.77
    lain
    -0.77
    utations
    -0.74
    arians
    -0.72
    icist
    -0.72
    ername
    -0.70
    hement
    -0.70
    ancies
    -0.69
    POSITIVE LOGITS
    church
    0.90
     Bates
    0.89
    bats
    0.78
     Bee
    0.74
    ples
    0.70
     Lyons
    0.68
    wolves
    0.66
    BLE
    0.65
     Hoo
    0.64
     Strikes
    0.64
    Activations Density 0.024%

    No Known Activations