© 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. 2-RES-JB
    11. 21485
    Prev
    Next
    INDEX
    Explanations

    phrases related to precision or accuracy

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "precise" and its variations, indicating a focus on accuracy and exactness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mushroom
    -0.75
    ublic
    -0.74
    imaru
    -0.72
    BuyableInstoreAndOnline
    -0.69
    neys
    -0.69
    bane
    -0.68
    Connector
    -0.68
    ned
    -0.68
    Demand
    -0.67
    GW
    -0.67
    POSITIVE LOGITS
     accuracy
    0.94
     precision
    0.93
     precise
    0.88
     timing
    0.87
     pinpoint
    0.87
     accurate
    0.84
     calibrated
    0.84
     wording
    0.83
     amounts
    0.82
     positioning
    0.82
    Activations Density 0.005%

    No Known Activations