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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11726
    Prev
    Next
    INDEX
    Explanations

    terms related to firearms and gun control

    oai_token-act-pair · gpt-3.5-turbo

    references to gun-related topics and issues

    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
     Borders
    -0.75
     Richards
    -0.70
     pillars
    -0.69
     intervals
    -0.68
     Shards
    -0.66
     amaz
    -0.65
     Jed
    -0.65
     pleasantly
    -0.63
     Cind
    -0.63
     observations
    -0.60
    POSITIVE LOGITS
    carry
    1.31
    related
    1.27
    safety
    1.23
    themed
    1.22
    indust
    1.18
    loving
    1.17
    free
    1.16
    training
    1.13
    based
    1.10
    policy
    1.10
    Activations Density 0.081%

    No Known Activations