© 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. 1-RES-JB
    11. 10240
    Prev
    Next
    INDEX
    Explanations

    words related to ambiguity and uncertainty

    oai_token-act-pair · gpt-3.5-turbo

    terms related to ambivalence and the concept of duality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zyme
    -0.70
    built
    -0.69
     simpl
    -0.65
    lessly
    -0.63
     clipboard
    -0.61
     perpetually
    -0.60
    olesterol
    -0.60
     cross
    -0.59
    blown
    -0.57
    ettle
    -0.57
    POSITIVE LOGITS
    ival
    1.48
    iott
    0.87
    terness
    0.78
    ÃįÃį
    0.78
    quickShipAvailable
    0.77
    DragonMagazine
    0.76
    ados
    0.74
    eties
    0.73
    antics
    0.73
    ivals
    0.73
    Activations Density 0.007%

    No Known Activations