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

    Neuronpedia

    Jacobian LensNEW
    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. 15809
    Prev
    Next
    INDEX
    Explanations

    words related to different types of technology, such as AI, development, infrastructure, and software

    oai_token-act-pair · gpt-3.5-turbo

    mentions of artificial intelligence and related technologies

    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
    ongyang
    -0.62
     transf
    -0.60
     rud
    -0.60
     inver
    -0.60
     è£ıè
    -0.60
    accompan
    -0.59
     incon
    -0.58
    drm
    -0.57
     autop
    -0.57
     uninsured
    -0.57
    POSITIVE LOGITS
    issance
    1.00
     Lauder
    0.92
     Abbey
    0.88
    enment
    0.83
    xual
    0.79
    ciating
    0.76
    ption
    0.75
    ction
    0.71
    ment
    0.71
    ional
    0.68
    Activations Density 0.445%

    No Known Activations