© 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. 1360
    Prev
    Next
    INDEX
    Explanations

    mentions of or references to the word "Saint"

    oai_token-act-pair · gpt-3.5-turbo

    references to saint-related terms or entities

    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
    HO
    -0.72
    PT
    -0.72
    ORN
    -0.67
    ERG
    -0.64
    BIP
    -0.63
     sled
    -0.62
    clips
    -0.61
    itsch
    -0.60
     mishand
    -0.60
    mable
    -0.59
    POSITIVE LOGITS
     Laurent
    1.05
     Lucia
    0.99
     Clair
    0.94
     Petersburg
    0.93
    clair
    0.91
     Augustine
    0.90
     Louis
    0.90
     Francis
    0.84
     Kitt
    0.81
    ctuary
    0.80
    Activations Density 0.016%

    No Known Activations