© 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. 3-RES-JB
    11. 5814
    Prev
    Next
    INDEX
    Explanations

    references to the name "Cr"

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the name "Crick."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    姫
    -0.87
    eers
    -0.78
     quo
    -0.77
     Ukrainian
    -0.75
    DragonMagazine
    -0.71
    heid
    -0.71
     Remastered
    -0.71
    HCR
    -0.71
    folk
    -0.69
    IELD
    -0.68
    POSITIVE LOGITS
    adle
    1.15
    umb
    0.99
    utch
    0.97
    acker
    0.94
    umbs
    0.94
    anks
    0.92
    uder
    0.92
    ump
    0.91
    acked
    0.90
    acking
    0.89
    Activations Density 0.008%

    No Known Activations