© 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. 4-RES-JB
    11. 15516
    Prev
    Next
    INDEX
    Explanations

    words related to redirecting or changing the course of something

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of diverting or redirecting

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

    No Comments

    Negative Logits
    è¦ļéĨĴ
    -0.66
    iPhone
    -0.63
    fters
    -0.62
    ears
    -0.61
    oven
    -0.58
    bon
    -0.57
    Requires
    -0.57
     Leather
    -0.56
    âĺħ
    -0.56
    */(
    -0.55
    POSITIVE LOGITS
     divert
    1.07
     diverted
    0.87
    ancing
    0.86
     diversion
    0.83
    wcs
    0.82
    irect
    0.81
    icular
    0.80
    ugu
    0.79
    ewater
    0.77
    aline
    0.76
    Activations Density 0.012%

    No Known Activations