© 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. 11460
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical information or product details

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "NN" and related acronyms 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
    rero
    -0.72
    holding
    -0.65
    rament
    -0.64
    choes
    -0.62
     vested
    -0.60
     differential
    -0.60
    raviolet
    -0.60
     mileage
    -0.59
     odds
    -0.58
     persistent
    -0.57
    POSITIVE LOGITS
    NN
    1.42
    nn
    1.14
    estern
    0.95
    pedia
    0.93
    aturally
    0.93
    erd
    0.91
    icol
    0.88
    eat
    0.87
     Ago
    0.84
    arie
    0.84
    Activations Density 0.005%

    No Known Activations