© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 2627
    Prev
    Next
    INDEX
    Explanations

    keywords related to legal issues and crime

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

    words that indicate a lack or absence of something

    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
     Duchess
    -0.72
     heartbeat
    -0.70
     Universe
    -0.69
     gulf
    -0.68
     drip
    -0.68
     die
    -0.68
     whipping
    -0.67
     parting
    -0.67
     worry
    -0.67
     darling
    -0.67
    POSITIVE LOGITS
    licensed
    1.44
    approved
    1.41
    registered
    1.39
    author
    1.38
    verified
    1.31
    sec
    1.28
    claimed
    1.25
    encrypted
    1.24
    super
    1.23
    authorized
    1.20
    Activations Density 0.049%

    No Known Activations