© 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. 3-RES-JB
    11. 15088
    Prev
    Next
    INDEX
    Explanations

    names or proper nouns related to various individuals

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and specific names related to individuals and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    owing
    -0.76
    cano
    -0.74
    cess
    -0.73
    ame
    -0.72
    erton
    -0.72
    enium
    -0.69
    anted
    -0.68
    ames
    -0.67
    ington
    -0.66
    ridge
    -0.66
    POSITIVE LOGITS
     Beir
    0.85
    SHIP
    0.84
     Zah
    0.81
     Kahn
    0.80
     Hollande
    0.75
    ++++++++++++++++
    0.75
     Macron
    0.73
    Fine
    0.71
    bars
    0.70
     Akin
    0.70
    Activations Density 0.040%

    No Known Activations