© 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. 9-RES-JB
    11. 13899
    Prev
    Next
    INDEX
    Explanations

    the word "perfectly" followed by an adjective

    oai_token-act-pair · gpt-3.5-turbo

    the word "perfectly" in various contexts, often emphasizing its significance

    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
    jri
    -0.83
    anwhile
    -0.78
    ulative
    -0.75
    NetMessage
    -0.74
    SEE
    -0.73
    uese
    -0.70
    gee
    -0.69
    grave
    -0.67
    hee
    -0.65
    mere
    -0.64
    POSITIVE LOGITS
     suited
    1.09
     aligned
    1.05
     timed
    1.03
     calibrated
    0.95
     positioned
    0.93
     behaved
    0.88
     encaps
    0.88
     situated
    0.83
     synchronized
    0.82
     adapted
    0.82
    Activations Density 0.033%

    No Known Activations