© 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. 11-RES-JB
    11. 5018
    Prev
    Next
    INDEX
    Explanations

    phrases related to destruction or ruining

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with destruction and negative impacts on people or property

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.82
    rants
    -0.79
    dding
    -0.74
    mad
    -0.73
    ERROR
    -0.71
    orney
    -0.69
    ocating
    -0.69
    FML
    -0.68
    zbek
    -0.67
    acus
    -0.67
    POSITIVE LOGITS
     havoc
    1.31
     lives
    1.04
     livelihood
    0.99
     friendships
    0.99
     priceless
    0.98
     bridges
    0.97
     careers
    0.96
     everything
    0.94
     morale
    0.94
     civilization
    0.91
    Activations Density 0.186%

    No Known Activations