© 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. 4-RES-JB
    11. 15228
    Prev
    Next
    INDEX
    Explanations

    words related to locations or proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and elements related to names and titles

    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
    frames
    -0.74
     Cheong
    -0.72
     stiffness
    -0.65
    liners
    -0.62
     Saban
    -0.60
    blank
    -0.60
     flo
    -0.60
     scrap
    -0.58
     reckoning
    -0.57
     Shutterstock
    -0.57
    POSITIVE LOGITS
    ioxide
    0.91
    CLE
    0.88
    ornia
    0.83
    estine
    0.80
    aires
    0.79
    atible
    0.78
    ãĤ¼ãĤ¦ãĤ¹
    0.78
    anut
    0.77
    aneous
    0.77
    eta
    0.75
    Activations Density 0.276%

    No Known Activations