© 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. 6-RES-JB
    11. 5505
    Prev
    Next
    INDEX
    Explanations

    that something can no longer be done or relied upon

    oai_token-act-pair · gpt-3.5-turbo

    negations and phrases indicating impossibility or inability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BuyableInstoreAndOnline
    -0.73
    DragonMagazine
    -0.64
    ONES
    -0.64
    soDeliveryDate
    -0.60
    Kings
    -0.59
     Kush
    -0.59
    Land
    -0.56
    HOME
    -0.56
     guiActiveUnfocused
    -0.55
    oresc
    -0.55
    POSITIVE LOGITS
    rouse
    1.19
    venge
    1.18
    rely
    0.88
    etheless
    0.87
    lessly
    0.85
    activate
    0.82
    arily
    0.80
    ize
    0.79
    ean
    0.79
    ceive
    0.77
    Activations Density 0.305%

    No Known Activations