© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 962
    Prev
    Next
    INDEX
    Explanations

    words related to catalysts or things that trigger significant changes or reactions

    oai_token-act-pair · gpt-3.5-turbo
    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
    iciency
    -0.83
    awar
    -0.81
    mbuds
    -0.73
    andro
    -0.73
    opal
    -0.72
    stretched
    -0.72
    oho
    -0.72
     Lomb
    -0.70
    jong
    -0.68
    ©¶æ
    -0.68
    POSITIVE LOGITS
     catalyst
    1.37
     cataly
    1.21
     ignite
    0.81
    ="#
    0.79
     inhibitor
    0.79
     ignited
    0.73
     precursor
    0.71
     flare
    0.71
     converter
    0.71
    Connector
    0.70
    Activations Density 0.012%

    No Known Activations