© 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. 7391
    Prev
    Next
    INDEX
    Explanations

    phrases expressing the importance of actions or decisions

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the importance of taking action or making decisions

    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
    HD
    -0.66
     dilig
    -0.64
    Orig
    -0.62
    ¸
    -0.60
    ;;;;;;;;
    -0.59
    abytes
    -0.58
    è£
    -0.57
    quickShipAvailable
    -0.57
    soDeliveryDate
    -0.56
    mails
    -0.54
    POSITIVE LOGITS
    adies
    0.85
    wered
    0.85
    ankind
    0.82
    ggles
    0.78
    ads
    0.77
    ogle
    0.75
    ilet
    0.75
     avoid
    0.75
    othy
    0.74
     revisit
    0.73
    Activations Density 0.163%

    No Known Activations