© 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. 3628
    Prev
    Next
    INDEX
    Explanations

    references to "burrows"

    oai_token-act-pair · gpt-3.5-turbo

    references to rows or collections of items

    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
     circumstance
    -0.70
    «ĺ
    -0.67
     Kenyan
    -0.64
     retake
    -0.63
     PLAN
    -0.61
     quasi
    -0.61
     isolate
    -0.60
     nomine
    -0.60
     maritime
    -0.59
     circumstances
    -0.59
    POSITIVE LOGITS
    rows
    1.49
    restling
    1.02
    icz
    0.99
    row
    0.95
    rowing
    0.89
    olver
    0.83
    irds
    0.83
    unda
    0.79
    ars
    0.79
    hip
    0.79
    Activations Density 0.007%

    No Known Activations