© 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. 7-RES-JB
    11. 17252
    Prev
    Next
    INDEX
    Explanations

    superlatives describing excellence, such as "best," "hottest," and "most."

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "one of the best" followed by a specific category or context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Query
    -0.72
    612
    -0.69
    EngineDebug
    -0.69
    DragonMagazine
    -0.65
    acter
    -0.65
    fter
    -0.63
    ALSE
    -0.62
    122
    -0.62
    659
    -0.60
    642
    -0.60
    POSITIVE LOGITS
     existence
    0.97
    efficiency
    0.93
    ducers
    0.85
     terms
    0.82
    clusively
    0.81
    herent
    0.81
    ordinate
    0.79
    effic
    0.79
    clusions
    0.78
    escap
    0.77
    Activations Density 0.114%

    No Known Activations