© 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. 12-RES-JB
    11. 4281
    Prev
    Next
    INDEX
    Explanations

    news related to criminal activities such as murders, child abuse, and legal charges

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    instances of severe legal repercussions related to criminal activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
     tremend
    -1.01
     challeng
    -0.99
     satell
    -0.98
     transact
    -0.91
     skelet
    -0.90
     gobl
    -0.89
     stocking
    -0.89
     occas
    -0.89
     expended
    -0.88
     therape
    -0.88
    POSITIVE LOGITS
    Interested
    1.19
    According
    1.08
    Speaking
    1.05
    Writing
    1.04
    Following
    1.01
    Beginning
    0.99
    Released
    0.99
    ↵↵
    0.98
    Multiple
    0.98
    Starting
    0.98
    Activations Density 0.347%

    No Known Activations