© 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. 3-RES-JB
    11. 24374
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "Before"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Before" in temporal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olog
    -0.73
    aren
    -0.73
    utter
    -0.69
    amount
    -0.67
    PROV
    -0.66
    NRS
    -0.65
    wire
    -0.65
    erry
    -0.65
    è¦ļéĨĴ
    -0.64
    alian
    -0.62
    POSITIVE LOGITS
    pping
    0.74
    nder
    0.71
    noon
    0.71
     sunset
    0.68
     Stats
    0.67
    rely
    0.66
    empt
    0.66
    irement
    0.65
     Worlds
    0.65
     retiring
    0.64
    Activations Density 0.036%

    No Known Activations