© 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. 15100
    Prev
    Next
    INDEX
    Explanations

    This neuron is activated by properly spelled words containing "ion"

    oai_token-act-pair · gpt-3.5-turbo

    the presence of specific characters or symbols typically associated with formatting or encoding issues in text

    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
     Engel
    -0.67
     Chop
    -0.65
    åį
    -0.64
     Ridley
    -0.64
     Dempsey
    -0.62
     Raf
    -0.61
    DragonMagazine
    -0.60
     Ãľ
    -0.60
     Rez
    -0.59
     srfAttach
    -0.59
    POSITIVE LOGITS
    nesota
    0.79
    ith
    0.75
    lated
    0.73
    gress
    0.72
    der
    0.72
    duct
    0.72
    stru
    0.71
    ject
    0.71
    duc
    0.71
    cus
    0.70
    Activations Density 0.020%

    No Known Activations