© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 20631
    Prev
    Next
    INDEX
    Explanations

    concerns expressed as questions

    oai_token-act-pair · gpt-3.5-turbo

    questions that begin with "Did" or "Does."

    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
    è¦ļéĨĴ
    -0.80
    å§«
    -0.76
    ãģĮ
    -0.76
    displayText
    -0.75
    perty
    -0.73
    Ñģ
    -0.72
    ãģ«
    -0.69
    arez
    -0.68
    ãģ§
    -0.66
    umbn
    -0.66
    POSITIVE LOGITS
    olated
    0.79
    berra
    0.77
    fred
    0.74
    n
    0.74
    olate
    0.71
    olation
    0.67
     anyone
    0.67
    aston
    0.64
    nt
    0.63
     millenn
    0.62
    Activations Density 0.071%

    No Known Activations