© 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. 22633
    Prev
    Next
    INDEX
    Explanations

    references to social media interactions

    oai_token-act-pair · gpt-3.5-turbo

    repetitions of a particular character or symbol

    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
     semic
    -0.75
     scattering
    -0.73
     diffusion
    -0.69
     prepar
    -0.67
     dividing
    -0.66
     qualitative
    -0.66
     folding
    -0.66
     dispers
    -0.64
     Unified
    -0.64
     Provincial
    -0.63
    POSITIVE LOGITS
    į
    1.12
    ¹
    1.10
    ¬
    1.08
    Į
    1.07
    ½
    1.06
    ª
    1.06
    ı
    1.05
    ¡
    1.03
    ¼
    1.00
    Ń
    0.99
    Activations Density 0.542%

    No Known Activations