© 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. 7-RES-JB
    11. 2184
    Prev
    Next
    INDEX
    Explanations

    words related to laws, regulations, or official actions

    oai_token-act-pair · gpt-3.5-turbo

    references to legislative or regulatory measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    osta
    -0.78
    sites
    -0.76
     Reserve
    -0.72
     Forsaken
    -0.70
     Ruin
    -0.68
    opath
    -0.68
    assets
    -0.68
    oooooooooooooooo
    -0.67
    si
    -0.66
    ciating
    -0.66
    POSITIVE LOGITS
    MENTS
    0.86
    witz
    0.82
    ment
    0.80
    arian
    0.78
    ters
    0.76
    hof
    0.74
    ments
    0.73
    terday
    0.73
    ter
    0.72
    xual
    0.71
    Activations Density 0.020%

    No Known Activations