© 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. 23647
    Prev
    Next
    INDEX
    Explanations

    mentions of legal actions or accusations

    oai_token-act-pair · gpt-3.5-turbo

    subjects and their actions in a legal or regulatory context

    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
    raft
    -0.80
    ournal
    -0.79
    hetti
    -0.73
    adium
    -0.72
    geries
    -0.71
    reating
    -0.71
    ictional
    -0.71
    ancial
    -0.71
    urgical
    -0.69
    ourgeois
    -0.68
    POSITIVE LOGITS
     sorely
    0.88
     dearly
    0.85
     gladly
    0.81
     describes
    0.79
     deems
    0.78
     presumably
    0.78
     evidently
    0.77
     swore
    0.77
     deem
    0.76
     dubbed
    0.76
    Activations Density 0.184%

    No Known Activations