© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 12780
    Prev
    Next
    INDEX
    Explanations

    financial amounts in euros

    oai_token-act-pair · gpt-3.5-turbo

    currency symbols and their associated amounts

    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
    uyomi
    -0.75
    atives
    -0.65
    oted
    -0.64
     Alley
    -0.63
    umbn
    -0.63
     Peb
    -0.63
     Bangl
    -0.63
     Khe
    -0.63
    etsk
    -0.62
     Zucker
    -0.62
    POSITIVE LOGITS
    £
    1.09
     âĤ¬
    1.05
    Ëľ
    1.02
    âĤ¬
    0.97
    USD
    0.87
    $
    0.85
    cos
    0.83
     (£
    0.75
    $$$$
    0.75
    ï
    0.73
    Activations Density 0.007%

    No Known Activations