© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10-RES-JB
    11. 10618
    Prev
    Next
    INDEX
    Explanations

    words related to explosions or violent events

    oai_token-act-pair · gpt-3.5-turbo

    references to explosions or blasts

    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
    guyen
    -0.74
    nda
    -0.68
     Solitaire
    -0.67
    lich
    -0.64
    éĸ
    -0.63
    Lean
    -0.62
    Trust
    -0.62
    ilyn
    -0.61
     Cla
    -0.59
    abor
    -0.59
    POSITIVE LOGITS
     furnace
    1.21
     radius
    1.06
     furn
    0.97
    hower
    0.96
     Heard
    0.91
    waves
    0.90
     blast
    0.85
     blasts
    0.84
    storms
    0.79
    waters
    0.78
    Activations Density 0.052%

    No Known Activations