© 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. 10-RES-JB
    11. 13798
    Prev
    Next
    INDEX
    Explanations

    words related to coding and special characters

    oai_token-act-pair · gpt-3.5-turbo

    symbols related to formatting or coding structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Surviv
    -0.79
     fairness
    -0.73
     millenn
    -0.68
     assum
    -0.65
     commissions
    -0.64
     pensions
    -0.64
     surviv
    -0.63
     Mirage
    -0.62
     catering
    -0.60
     Unlimited
    -0.60
    POSITIVE LOGITS
     denotes
    1.22
     suffix
    1.15
    -.
    1.09
     denote
    1.08
     vowel
    1.07
     prefix
    1.05
    É
    1.04
    ï¸ı
    1.04
     signifies
    1.01
    Ïī
    1.00
    Activations Density 0.163%

    No Known Activations