© 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. 19861
    Prev
    Next
    INDEX
    Explanations

    words related to edges or boundaries

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "edge," particularly in various contexts

    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
    anism
    -0.84
    OUP
    -0.71
    ions
    -0.66
    ÄŁ
    -0.65
    heny
    -0.64
    ION
    -0.64
     subsidized
    -0.62
    ttle
    -0.62
    asca
    -0.62
    OY
    -0.62
    POSITIVE LOGITS
    hog
    1.04
     Catalyst
    0.96
     rusher
    0.95
    phal
    0.84
    combe
    0.84
     edge
    0.82
    lessly
    0.79
    manship
    0.75
    bite
    0.75
    lessness
    0.70
    Activations Density 0.060%

    No Known Activations