© 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. 19305
    Prev
    Next
    INDEX
    Explanations

    words related to destruction and damage

    oai_token-act-pair · gpt-3.5-turbo

    instances of destruction and damaging events related to buildings and infrastructure

    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
     inconsistency
    -0.72
    verse
    -0.71
    ophe
    -0.66
     hypocr
    -0.64
    lihood
    -0.64
    76561
    -0.63
     subtle
    -0.62
    jiang
    -0.60
     nuances
    -0.59
    cial
    -0.59
    POSITIVE LOGITS
     redevelopment
    0.97
     redevelop
    0.94
     dere
    0.92
     UNESCO
    0.92
     demolition
    0.89
     renovation
    0.89
     rubble
    0.85
     lockdown
    0.82
     reopened
    0.80
     seism
    0.80
    Activations Density 0.667%

    No Known Activations