© 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. 1-RES-JB
    11. 24266
    Prev
    Next
    INDEX
    Explanations

    phrases conveying prohibition or restriction

    oai_token-act-pair · gpt-3.5-turbo

    terms related to prohibitive regulations or bans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ammy
    -0.86
    pring
    -0.78
     Forsaken
    -0.74
    swick
    -0.71
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.71
    eon
    -0.71
    athering
    -0.70
    Leary
    -0.69
    Pros
    -0.67
     Warcraft
    -0.66
    POSITIVE LOGITS
     prohibits
    1.12
     prohibited
    1.11
     prohibit
    1.08
    ĸļ
    1.04
     prohibiting
    1.01
     forbids
    1.00
     prohibition
    0.89
     restricting
    0.87
     preclude
    0.86
     restricts
    0.85
    Activations Density 0.016%

    No Known Activations