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

    Neuronpedia

    Jacobian LensNEW
    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. 9-RES-JB
    11. 15798
    Prev
    Next
    INDEX
    Explanations

    references to a specific character named Merc

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "Merc" or related variations, indicating a focus on commerce or business

    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
    mble
    -0.76
    FORMATION
    -0.71
    nik
    -0.68
    ference
    -0.65
    chy
    -0.65
    rine
    -0.65
    KEN
    -0.62
    PUT
    -0.61
     Devi
    -0.61
    put
    -0.61
    POSITIVE LOGITS
    iless
    1.36
    enaries
    1.13
    ifully
    1.12
    iful
    1.09
    andise
    0.94
    auga
    0.84
    uries
    0.84
    antle
    0.79
    ies
    0.79
    istrate
    0.78
    Activations Density 0.100%

    No Known Activations