© 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. 8-RES-JB
    11. 19376
    Prev
    Next
    INDEX
    Explanations

    phrases related to danger or negative consequences

    oai_token-act-pair · gpt-3.5-turbo

    phrases and concepts related to near-death experiences and associated implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     DRAG
    -0.80
     Tycoon
    -0.75
    ulhu
    -0.71
    Ĥª
    -0.71
     Doodle
    -0.69
     Zup
    -0.66
     Cohn
    -0.66
     Gillespie
    -0.65
     Wanted
    -0.64
     Wiz
    -0.64
    POSITIVE LOGITS
    sighted
    1.20
    perfect
    1.07
    zero
    1.03
    const
    1.02
    term
    1.01
    surface
    0.97
    exclusive
    0.97
    sil
    0.95
    earth
    0.94
    future
    0.93
    Activations Density 0.024%

    No Known Activations