© 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. 11-RES-JB
    11. 20640
    Prev
    Next
    INDEX
    Explanations

    phrases related to statements made by individuals

    oai_token-act-pair · gpt-3.5-turbo

    quoted speech or dialogue within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bsite
    -0.67
     NGOs
    -0.65
     constituents
    -0.64
     jurisd
    -0.64
     interven
    -0.64
     Betsy
    -0.64
     prosecutions
    -0.64
     divest
    -0.63
     hundreds
    -0.63
     parliament
    -0.62
    POSITIVE LOGITS
    Coach
    1.07
     Pwr
    0.94
    Thumbnail
    0.92
    Said
    0.91
     coach
    0.90
    ESPN
    0.89
     FANTASY
    0.89
     Coach
    0.89
     Rookie
    0.87
     Cavs
    0.84
    Activations Density 0.150%

    No Known Activations