© 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. 9-RES-JB
    6. 8688
    Prev
    Next
    INDEX
    Explanations

    terms related to negative or harmful actions or situations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to conflict and ongoing struggles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dearly
    -0.65
     brightly
    -0.64
     Laure
    -0.63
    cients
    -0.62
    versely
    -0.61
     cultured
    -0.60
     Clapper
    -0.59
    dL
    -0.58
    orously
    -0.58
    inally
    -0.58
    POSITIVE LOGITS
    arenthood
    0.86
    ounters
    0.84
    urden
    0.82
    lessness
    0.81
    externalActionCode
    0.78
    ãĤ¼ãĤ¦ãĤ¹
    0.78
    illation
    0.78
    earances
    0.77
    uation
    0.75
    ptions
    0.71
    Activations Density 0.543%

    No Known Activations