© 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. 7569
    Prev
    Next
    INDEX
    Explanations

    phrases mentioning a wide variety or range of items, features, or people

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a wide range or variety of options

    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
    cair
    -0.70
    CB
    -0.66
    LV
    -0.65
     Maid
    -0.64
    ICAN
    -0.64
    act
    -0.63
    erick
    -0.62
     Patron
    -0.62
    Dialogue
    -0.61
    anan
    -0.61
    POSITIVE LOGITS
    leaf
    0.99
     wide
    0.94
    creen
    0.90
    open
    0.86
     scope
    0.86
     wider
    0.85
     open
    0.85
     ranging
    0.84
    spread
    0.84
     breadth
    0.83
    Activations Density 0.017%

    No Known Activations