© 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. 1-RES-JB
    11. 14527
    Prev
    Next
    INDEX
    Explanations

    the word "surrogate" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    references to surrogates in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inness
    -0.91
    INESS
    -0.84
    ulhu
    -0.75
    azes
    -0.73
    alach
    -0.72
    OA
    -0.70
    oak
    -0.70
    IST
    -0.70
    endon
    -0.69
    ovie
    -0.69
    POSITIVE LOGITS
     surrog
    1.58
     surrogate
    1.37
     Parenthood
    0.73
     gest
    0.73
    riages
    0.70
     laun
    0.69
    ãĤ§
    0.68
     encour
    0.67
     airst
    0.65
     lod
    0.64
    Activations Density 0.007%

    No Known Activations