© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 19680
    Prev
    Next
    INDEX
    Explanations

    sections of legal codes

    oai_token-act-pair · gpt-3.5-turbo

    legal sections or articles related to specific laws or codes

    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
    aukee
    -0.75
     Markus
    -0.65
    >>\
    -0.65
     hur
    -0.65
    Russ
    -0.64
     laun
    -0.64
     Tycoon
    -0.63
    ãĥ¼ãĤ¯
    -0.63
     Blizz
    -0.62
     destro
    -0.61
    POSITIVE LOGITS
    witz
    0.91
    rimination
    0.78
    oral
    0.73
    omsky
    0.68
    alities
    0.68
    ometimes
    0.66
    olon
    0.66
     thereof
    0.65
    ipher
    0.64
    mination
    0.64
    Activations Density 0.024%

    No Known Activations