© 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. 17507
    Prev
    Next
    INDEX
    Explanations

    terms related to the word "alk"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "alk."

    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
    ACTED
    -0.72
    ============
    -0.70
    ======
    -0.69
    ODUCT
    -0.66
     Staples
    -0.65
    ================================================================
    -0.64
    GAME
    -0.62
    ------------------------------------------------
    -0.62
    ãģŁ
    -0.61
    PDATE
    -0.61
    POSITIVE LOGITS
    alk
    1.17
    enstein
    1.06
    owitz
    0.99
    iewicz
    0.94
    enburg
    0.93
    ers
    0.90
    reath
    0.90
    ulic
    0.86
    ering
    0.85
    ipedia
    0.85
    Activations Density 0.009%

    No Known Activations