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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2-RES-JB
    11. 23286
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Gorsuch"

    oai_token-act-pair · gpt-3.5-turbo

    references to Neil Gorsuch

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ion
    -0.84
     Maid
    -0.67
    iot
    -0.66
    agement
    -0.63
    ooters
    -0.63
    ipal
    -0.63
    #$
    -0.61
     Carnegie
    -0.60
     Virgin
    -0.60
    ãĥ¡
    -0.60
    POSITIVE LOGITS
    milo
    1.11
     Gorsuch
    1.07
    enthal
    0.84
    enei
    0.84
     TAMADRA
    0.79
    é¾įå¥ij士
    0.77
    ierrez
    0.75
    atown
    0.75
    代
    0.71
     panels
    0.71
    Activations Density 0.009%

    No Known Activations