© 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. 4-RES-JB
    11. 22294
    Prev
    Next
    INDEX
    Explanations

    phrases related to self-introductions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the act of introducing oneself or others

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

    No Comments

    Negative Logits
     accrued
    -0.77
     overd
    -0.69
     fulfilled
    -0.68
    ï¸ı
    -0.67
     satisfied
    -0.65
    usercontent
    -0.64
     insured
    -0.64
    otten
    -0.62
    RELATED
    -0.61
     outcome
    -0.60
    POSITIVE LOGITS
     [|
    0.78
    äºĶ
    0.75
     Wave
    0.73
    catentry
    0.68
     Carbuncle
    0.68
     anew
    0.67
    skirts
    0.67
    ITNESS
    0.67
    Tai
    0.67
    è¦ļéĨĴ
    0.66
    Activations Density 0.102%

    No Known Activations