© 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. 10445
    Prev
    Next
    INDEX
    Explanations

    the last name "Sharapova"

    oai_token-act-pair · gpt-3.5-turbo

    the suffix "ova" in names and terms

    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
    reads
    -0.73
    ged
    -0.70
    gers
    -0.67
    brow
    -0.67
    Past
    -0.66
    posted
    -0.65
    Notable
    -0.64
    =-=-=-=-
    -0.64
    Score
    -0.64
    Subject
    -0.63
    POSITIVE LOGITS
    ova
    1.31
     Scotia
    1.29
    kees
    0.79
    OVA
    0.78
    qi
    0.78
    ania
    0.78
    ivari
    0.77
    oice
    0.76
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.76
    ansky
    0.75
    Activations Density 0.010%

    No Known Activations