© 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. 11-RES-JB
    11. 7604
    Prev
    Next
    INDEX
    Explanations

    names or terms starting with "Ta"

    oai_token-act-pair · gpt-3.5-turbo

    the name "Ta" and variations of it, indicating a focus on entities or notable figures that include this name

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pants
    -0.75
    lessly
    -0.74
    tons
    -0.67
     optics
    -0.63
    states
    -0.59
    cu
    -0.58
    lings
    -0.58
    tti
    -0.56
    gence
    -0.54
    vic
    -0.54
    POSITIVE LOGITS
    plin
    1.31
    vern
    1.16
    pling
    1.10
    xton
    1.09
    iley
    1.06
    issance
    1.06
    iba
    1.05
    plain
    1.04
    quer
    1.04
    resh
    1.02
    Activations Density 0.061%

    No Known Activations