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

    Neuronpedia

    Jacobian LensNEW
    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. 1115
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by a noun

    oai_token-act-pair · gpt-3.5-turbo

    phrases that refer to relationships or conditions associated with specific individuals or groups

    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
    leaf
    -0.72
     Checking
    -0.70
    let
    -0.69
    DI
    -0.68
    Repl
    -0.68
    âĨ
    -0.68
    pad
    -0.67
    0002
    -0.66
    Pad
    -0.66
    OOL
    -0.66
    POSITIVE LOGITS
    soever
    1.01
     ancestors
    0.95
     sole
    0.93
     own
    0.89
     transports
    0.81
     courage
    0.80
     fault
    0.77
     deepest
    0.75
     accompanies
    0.72
    oped
    0.72
    Activations Density 0.015%

    No Known Activations