© 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. 19071
    Prev
    Next
    INDEX
    Explanations

    words related to destruction or negative events

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with negative events or crises

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     cultured
    -0.83
     towed
    -0.75
     gifted
    -0.74
     minimalist
    -0.73
     explorer
    -0.72
     dummy
    -0.72
     bible
    -0.71
     decorated
    -0.71
     bartender
    -0.71
     designer
    -0.70
    POSITIVE LOGITS
    issions
    1.28
    downs
    1.24
    uations
    1.23
    acements
    1.22
    earances
    1.19
    ruption
    1.19
    ocations
    1.18
    aution
    1.18
    ulations
    1.17
    usions
    1.16
    Activations Density 0.332%

    No Known Activations