© 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. 9-RES-JB
    11. 14867
    Prev
    Next
    INDEX
    Explanations

    phrases related to weapons and shooting

    oai_token-act-pair · gpt-3.5-turbo

    references to weapons and violent actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "],"
    -0.66
    TOP
    -0.66
     friendships
    -0.64
    udget
    -0.61
     Situation
    -0.61
    TABLE
    -0.60
     recourse
    -0.59
    ĻĤ
    -0.59
    Anonymous
    -0.59
     discussions
    -0.57
    POSITIVE LOGITS
     onto
    1.15
     toward
    1.08
     darts
    1.06
     towards
    1.05
     projectiles
    0.98
     into
    0.94
    wards
    0.94
    balls
    0.92
     forcefully
    0.89
     dart
    0.87
    Activations Density 0.307%

    No Known Activations