© 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. 20225
    Prev
    Next
    INDEX
    Explanations

    terms related to transferring control or authority, such as "reins" and "leash."

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to control or dominance

    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
    mercial
    -0.87
    foundland
    -0.81
    iaries
    -0.78
     Glory
    -0.74
    estate
    -0.72
     Thou
    -0.71
    ism
    -0.69
    osity
    -0.68
    ingham
    -0.67
    acular
    -0.67
    POSITIVE LOGITS
     reins
    1.38
    merga
    0.79
     mos
    0.76
    urance
    0.76
    xual
    0.75
     guiding
    0.74
    ãĥĦ
    0.72
    hens
    0.72
     guiActiveUn
    0.71
    EStreamFrame
    0.70
    Activations Density 0.014%

    No Known Activations