© 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. 6-RES-JB
    11. 923
    Prev
    Next
    INDEX
    Explanations

    financial or monetary related terms

    oai_token-act-pair · gpt-3.5-turbo

    specific phrases and symbols, particularly quotation marks and certain characters, indicating dialogue or emphasis in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nickname
    -0.78
     pseudonym
    -0.74
     persona
    -0.72
     metaphor
    -0.71
     Mechdragon
    -0.70
     moniker
    -0.69
     QR
    -0.69
     naming
    -0.67
     proposition
    -0.67
     anonymity
    -0.66
    POSITIVE LOGITS
    ente
    0.83
    meric
    0.82
    important
    0.81
    ursed
    0.77
    iple
    0.74
    ighty
    0.72
    ishops
    0.71
    enser
    0.70
    enth
    0.68
    acies
    0.67
    Activations Density 0.273%

    No Known Activations