© 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. 9-RES-JB
    11. 18194
    Prev
    Next
    INDEX
    Explanations

    phrases indicating problems and solutions or fixing something

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to problem-solving and solutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ebus
    -0.66
     checkout
    -0.55
    gal
    -0.54
    rosis
    -0.53
     Coffin
    -0.53
    bah
    -0.53
    yrinth
    -0.52
    uador
    -0.51
     Bulgar
    -0.50
     Holiday
    -0.49
    POSITIVE LOGITS
     thereof
    1.19
     them
    1.07
     THEM
    1.04
     Them
    1.00
    them
    0.98
     thereto
    0.98
     therein
    0.93
     it
    0.80
     theirs
    0.79
    swers
    0.72
    Activations Density 0.901%

    No Known Activations