© 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. 1512
    Prev
    Next
    INDEX
    Explanations

    a specific term, likely a company name or product, associated with high activation values

    oai_token-act-pair · gpt-3.5-turbo

    symbols or characters that resemble the letter 'L'

    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
     mathemat
    -0.75
     deepening
    -0.66
     conspicuous
    -0.66
     lawy
    -0.66
    imeters
    -0.65
     strategically
    -0.65
     fertil
    -0.64
     levers
    -0.63
     permissible
    -0.62
     multiplying
    -0.62
    POSITIVE LOGITS
    ï¸ı
    1.09
    ship
    0.89
    tal
    0.88
    ski
    0.87
    ade
    0.86
    tyard
    0.85
    Balt
    0.83
    ulo
    0.82
    sic
    0.80
    tre
    0.79
    Activations Density 0.341%

    No Known Activations