© 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. 6-RES-JB
    11. 18394
    Prev
    Next
    INDEX
    Explanations

    words related to legal terms and law enforcement

    oai_token-act-pair · gpt-3.5-turbo

    special characters and line breaks in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    taboola
    -0.82
    ometimes
    -0.72
    ources
    -0.71
     Flavoring
    -0.70
     constitu
    -0.69
    hift
    -0.68
     Skydragon
    -0.64
    Ĥİ
    -0.64
     rall
    -0.64
    irie
    -0.64
    POSITIVE LOGITS
     corpus
    0.85
    icultural
    0.80
    inki
    0.78
    nian
    0.71
    phant
    0.70
    azard
    0.69
    rosis
    0.67
     Corpus
    0.67
    ndra
    0.65
    ilitation
    0.64
    Activations Density 0.076%

    No Known Activations