© 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. 0-RES-JB
    11. 5245
    Prev
    Next
    INDEX
    Explanations

    instances of the word "accord."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "accord."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Simulator
    -0.66
    oppers
    -0.64
    dule
    -0.64
    recated
    -0.63
    cular
    -0.61
    istical
    -0.61
    Browser
    -0.60
     Gamer
    -0.60
    opy
    -0.60
     Dug
    -0.60
    POSITIVE LOGITS
     accord
    4.32
     Accord
    2.54
     agreement
    1.44
     pact
    1.29
     harmony
    1.10
     harmon
    1.06
     Agreement
    1.05
     arrangement
    1.05
     acc
    1.03
     trumpet
    1.02
    Activations Density 0.004%

    No Known Activations