© 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. 8821
    Prev
    Next
    INDEX
    Explanations

    entities or terms related to electrical equipment or functions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of specific acronyms or abbreviations

    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
    hung
    -0.77
    ĸļ
    -0.77
    hood
    -0.77
    backer
    -0.74
     Austrian
    -0.73
     Colt
    -0.65
    ãĥĥãĥĪ
    -0.65
    ijn
    -0.64
    comes
    -0.63
     Stur
    -0.63
    POSITIVE LOGITS
    AC
    1.08
    ACA
    1.02
    ADA
    0.95
    olor
    0.92
    rylic
    0.90
    CEPT
    0.90
    AB
    0.90
    RIC
    0.89
    aucuses
    0.88
    HE
    0.87
    Activations Density 0.005%

    No Known Activations