© 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. 0-RES-JB
    11. 5255
    Prev
    Next
    INDEX
    Explanations

    phrases related to laws and regulations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to restrictive laws or regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TEXTURE
    -0.83
    kat
    -0.68
    Ni
    -0.67
     BEL
    -0.67
    akeru
    -0.66
    ear
    -0.66
    ãĥĸ
    -0.66
    apps
    -0.65
    pak
    -0.64
    bang
    -0.64
    POSITIVE LOGITS
     Restrict
    1.83
     Digest
    1.45
     Prohibition
    1.37
     Onion
    1.01
     Taken
    1.01
     Abstract
    0.78
    orgetown
    0.78
     Percent
    0.70
     Inquisition
    0.69
     Curiosity
    0.69
    Activations Density 0.006%

    No Known Activations