© 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. 436
    Prev
    Next
    INDEX
    Explanations

    phrases related to causal relationships or associations between different concepts, entities, or events

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a causal relationship or connection between entities

    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
     Penguins
    -0.74
    stall
    -0.67
     Sev
    -0.67
    Merit
    -0.64
     Nights
    -0.62
    sburg
    -0.62
    FUL
    -0.61
     Pens
    -0.61
     Liberties
    -0.60
    otos
    -0.60
    POSITIVE LOGITS
    linked
    0.91
    edin
    0.88
    chain
    0.77
     linking
    0.76
    irect
    0.74
    link
    0.73
    abolic
    0.69
     linked
    0.69
    abol
    0.68
     implicated
    0.68
    Activations Density 0.027%

    No Known Activations