© 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 EvalsExportsinterp-engineNEWAPI 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. 10-RES-JB
    11. 19079
    Prev
    Next
    INDEX
    Explanations

    terms related to anti-versions of substances or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases related to the concept of "anti"

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gork
    -0.69
    ĸļ
    -0.68
    phia
    -0.65
    pring
    -0.65
     Kinn
    -0.65
     Remastered
    -0.64
    ULAR
    -0.61
    yards
    -0.61
    cipled
    -0.60
    lished
    -0.60
    POSITIVE LOGITS
    inflammatory
    0.92
    acid
    0.89
    strate
    0.87
    zac
    0.87
    abuse
    0.87
    establishment
    0.85
     Dhabi
    0.84
    abortion
    0.83
    orb
    0.80
    drug
    0.77
    Activations Density 0.020%

    No Known Activations