© 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. 523
    Prev
    Next
    INDEX
    Explanations

    financial and programming-related terms or codes

    oai_token-act-pair · gpt-3.5-turbo

    currency symbols or related financial representations

    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
     gag
    -0.74
     release
    -0.66
     show
    -0.66
     pack
    -0.65
     Cly
    -0.65
     SAP
    -0.62
     Pand
    -0.62
     reveal
    -0.61
     nig
    -0.60
     Panama
    -0.60
    POSITIVE LOGITS
    ¢
    4.46
    £
    2.06
    ¡
    1.84
    ŀ
    1.79
    ª
    1.77
    §
    1.77
    Ĵ
    1.77
    ł
    1.75
    IJ
    1.75
    ¤
    1.72
    Activations Density 0.013%

    No Known Activations