© 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. 2-RES-JB
    11. 8300
    Prev
    Next
    INDEX
    Explanations

    mentions of imported goods or products

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pool
    -0.82
    hap
    -0.77
    phasis
    -0.73
    holes
    -0.73
    uyomi
    -0.73
    hole
    -0.72
     Draper
    -0.70
    romancer
    -0.68
    esa
    -0.67
    uther
    -0.67
    POSITIVE LOGITS
     imported
    0.97
     imports
    0.92
    unct
    0.82
     importing
    0.82
    urers
    0.82
    uning
    0.80
    uned
    0.80
     exported
    0.77
    ugal
    0.75
     exporting
    0.74
    Activations Density 0.009%

    No Known Activations