© 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. 2-RES-JB
    11. 18791
    Prev
    Next
    INDEX
    Explanations

    proper nouns or abbreviations containing the letter "K"

    oai_token-act-pair · gpt-3.5-turbo

    the letter 'K' 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
     CLSID
    -0.68
     decay
    -0.67
    terday
    -0.65
     expires
    -0.63
     mosqu
    -0.63
     constitu
    -0.62
    wcsstore
    -0.60
    ãĥ¼ãĥĨãĤ£
    -0.60
     behavi
    -0.60
     contraceptives
    -0.59
    POSITIVE LOGITS
    won
    1.04
    rieg
    1.03
    orea
    1.03
    irk
    0.95
    ISS
    0.95
    ernel
    0.95
    EEP
    0.94
    essel
    0.92
    laus
    0.92
    etch
    0.92
    Activations Density 0.035%

    No Known Activations