© 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. 6358
    Prev
    Next
    INDEX
    Explanations

    terms related to financial institutions and regulations

    oai_token-act-pair · gpt-3.5-turbo

    financial and administrative terminology related to duties and engagements

    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
    netflix
    -0.85
    HUD
    -0.72
     OLED
    -0.72
     Feldman
    -0.69
    atonin
    -0.68
     taps
    -0.67
    mask
    -0.65
    agonist
    -0.65
    tap
    -0.64
     Rowling
    -0.64
    POSITIVE LOGITS
    enture
    2.83
    uties
    1.44
     engagements
    1.29
     specimen
    1.22
    uers
    1.18
     Monetary
    1.17
    entimes
    1.13
    eon
    1.11
     specimens
    1.05
     Vers
    1.01
    Activations Density 0.068%

    No Known Activations