© 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. 11-RES-JB
    11. 10211
    Prev
    Next
    INDEX
    Explanations

    financial terms and numbers

    oai_token-act-pair · gpt-3.5-turbo

    numerical data related to prices and economic statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     "$:/
    -0.74
    enegger
    -0.73
     recruitment
    -0.70
     Volunte
    -0.67
     hire
    -0.66
     volunteers
    -0.65
     reapp
    -0.63
     occupant
    -0.63
    ocating
    -0.61
     recruiting
    -0.61
    POSITIVE LOGITS
    USD
    1.09
    BTC
    0.98
    ETH
    0.88
    thereum
    0.87
     EUR
    0.87
    JP
    0.86
     USD
    0.85
    daq
    0.84
     BTC
    0.84
    NM
    0.82
    Activations Density 0.136%

    No Known Activations