© 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. 2-RES-JB
    11. 17323
    Prev
    Next
    INDEX
    Explanations

    words specifically ending in '-op'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "op"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     LIA
    -0.75
     Monstrous
    -0.72
     EntityItem
    -0.70
    ãģ®éŃĶ
    -0.69
     Sins
    -0.69
    taboola
    -0.68
     Brotherhood
    -0.68
    âĸ¬
    -0.67
     Lauder
    -0.66
     Magicka
    -0.65
    POSITIVE LOGITS
    yright
    1.35
    inion
    1.30
    arent
    1.15
    aque
    1.12
    edia
    1.11
    op
    1.08
    ops
    1.07
    sych
    1.04
    olitan
    1.01
    rop
    1.00
    Activations Density 0.014%

    No Known Activations