© 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. 2268
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a contrast or clarification in language

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "not that" and its variations emphasizing distinctions or clarifications

    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
    aukee
    -0.69
    lain
    -0.68
    oplan
    -0.67
    apse
    -0.67
    intosh
    -0.64
    pta
    -0.62
    mun
    -0.61
    elin
    -0.61
    antha
    -0.60
    MODE
    -0.59
    POSITIVE LOGITS
     expecting
    0.71
     kidding
    0.65
     anybody
    0.64
     anyone
    0.63
     coincidence
    0.62
    vernment
    0.62
     fancy
    0.61
     mention
    0.60
     anymore
    0.60
     Loan
    0.60
    Activations Density 0.096%

    No Known Activations