© 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. 9-RES-JB
    11. 22731
    Prev
    Next
    INDEX
    Explanations

    words related to recipes or cooking instructions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to organization, structure, and composition

    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
    姫
    -1.04
     channels
    -0.81
     papers
    -0.79
     levers
    -0.79
    sites
    -0.76
    axies
    -0.75
     departments
    -0.75
    inas
    -0.74
     corners
    -0.72
     motions
    -0.72
    POSITIVE LOGITS
     consisting
    1.03
     akin
    0.97
     named
    0.90
     called
    0.87
     resembling
    0.86
     reminiscent
    0.85
    lete
    0.85
     nicknamed
    0.82
    forcer
    0.82
     similar
    0.81
    Activations Density 0.556%

    No Known Activations