© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 10-RES-JB
    11. 16529
    Prev
    Next
    INDEX
    Explanations

    situations where problems are being solved

    oai_token-act-pair · gpt-3.5-turbo

    references to problem-solving processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tim
    -0.77
    nesty
    -0.72
     includ
    -0.71
    treated
    -0.71
    aware
    -0.70
    eners
    -0.70
    leans
    -0.69
    aws
    -0.69
    warm
    -0.69
    icipated
    -0.69
    POSITIVE LOGITS
     problems
    1.27
     puzzles
    1.27
     mysteries
    1.08
     Problems
    1.06
    problem
    1.01
     Puzzles
    1.01
    Problem
    1.00
     problem
    1.00
     Mysteries
    0.99
     solve
    0.99
    Activations Density 0.057%

    No Known Activations