© 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. 1965
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "at best"

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating subjective evaluations or opinions

    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
    nance
    -0.66
    HAM
    -0.65
    Cro
    -0.62
    irez
    -0.61
    ptive
    -0.61
    ivari
    -0.61
    IDA
    -0.61
     Ended
    -0.60
     Provision
    -0.60
    testing
    -0.59
    POSITIVE LOGITS
     times
    1.45
     best
    1.14
     odds
    0.98
    onal
    0.96
     worst
    0.95
     first
    0.93
    yp
    0.91
     pains
    0.90
    roph
    0.89
    best
    0.89
    Activations Density 0.096%

    No Known Activations