© 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. 9-RES-JB
    11. 18576
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Mercedes."

    oai_token-act-pair · gpt-3.5-turbo

    references to the brand Mercedes-Benz

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    omial
    -0.83
    urrent
    -0.82
    rified
    -0.77
    ting
    -0.77
     externalToEVAOnly
    -0.75
    ulnerability
    -0.74
    oat
    -0.74
    aci
    -0.73
    ally
    -0.71
    atches
    -0.71
    POSITIVE LOGITS
     Benz
    1.02
    terday
    0.86
     versa
    0.86
    -+
    0.83
    ë
    0.83
    abeth
    0.78
    Benz
    0.75
    yne
    0.73
    mith
    0.73
    ages
    0.70
    Activations Density 0.106%

    No Known Activations