© 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. 2-RES-JB
    11. 14342
    Prev
    Next
    INDEX
    Explanations

    keywords or phrases related to the word "pas" in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to "pas" or "paso" in various contexts

    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
    IGHTS
    -0.71
    =#
    -0.71
    é¾
    -0.70
    ocating
    -0.69
    ski
    -0.67
    ickson
    -0.66
    sheet
    -0.64
    itatively
    -0.64
    è¦ļéĨĴ
    -0.63
    amous
    -0.62
    POSITIVE LOGITS
    sth
    1.28
    chal
    1.25
    adena
    1.00
     pas
    0.97
    ques
    0.97
     Pas
    0.93
    sel
    0.89
    nown
    0.88
    chall
    0.86
    quin
    0.86
    Activations Density 0.008%

    No Known Activations