© 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. 6-RES-JB
    11. 18380
    Prev
    Next
    INDEX
    Explanations

    phrases related to criminal activities or incidents

    oai_token-act-pair · gpt-3.5-turbo

    events related to violent incidents or acts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Locations
    -0.70
    tarians
    -0.68
    DragonMagazine
    -0.67
     Languages
    -0.65
    ":["
    -0.60
    inctions
    -0.59
    natureconservancy
    -0.59
    ernels
    -0.58
     legends
    -0.58
    rians
    -0.57
    POSITIVE LOGITS
     allegedly
    0.71
     abusive
    0.68
     mistakenly
    0.66
     raping
    0.65
     accidentally
    0.64
     unsuccessfully
    0.64
     underage
    0.63
     improperly
    0.62
     inappropriately
    0.61
     overheard
    0.61
    Activations Density 0.914%

    No Known Activations