© 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. 0-RES-JB
    11. 12202
    Prev
    Next
    INDEX
    Explanations

    words related to averages or statistical measures

    oai_token-act-pair · gpt-3.5-turbo

    references to statistical averages and metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    backer
    -0.68
    ARA
    -0.65
    ye
    -0.65
    works
    -0.64
    rette
    -0.64
    ilic
    -0.61
     forcefully
    -0.60
     sovere
    -0.60
    xes
    -0.60
     Upon
    -0.59
    POSITIVE LOGITS
     average
    3.78
    average
    2.94
     Average
    2.57
     averages
    2.38
    Average
    2.32
     avg
    2.15
     median
    1.98
     averaging
    1.76
     averaged
    1.75
    Avg
    1.57
    Activations Density 0.017%

    No Known Activations