© 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. 3-RES-JB
    11. 12219
    Prev
    Next
    INDEX
    Explanations

    words related to physical destruction or damage

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "destruction."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    liner
    -0.81
    aque
    -0.76
    ramid
    -0.74
    atar
    -0.71
    rocal
    -0.71
    olate
    -0.71
    cium
    -0.70
    quart
    -0.67
    estone
    -0.65
    cific
    -0.65
    POSITIVE LOGITS
     havoc
    1.03
     inflicted
    0.94
     derby
    0.84
    roying
    0.81
     destruction
    0.80
     wrought
    0.80
     wre
    0.80
     spree
    0.77
     thereof
    0.76
     devastation
    0.76
    Activations Density 0.013%

    No Known Activations