© 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. 8-RES-JB
    11. 1961
    Prev
    Next
    INDEX
    Explanations

    phrases related to giving instructions or requests

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks or sentence-ending structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     regenerate
    -0.86
     regener
    -0.79
    ŃĶ
    -0.75
     affili
    -0.75
     shedding
    -0.72
     microbiome
    -0.71
    inventoryQuantity
    -0.70
     darker
    -0.69
     salute
    -0.69
     blending
    -0.68
    POSITIVE LOGITS
     Eventually
    1.39
     Unfortunately
    1.37
     Then
    1.27
     Luckily
    1.20
     Later
    1.20
     Soon
    1.16
     Instead
    1.16
     Meanwhile
    1.15
     Afterwards
    1.13
     Ultimately
    1.12
    Activations Density 0.377%

    No Known Activations