© 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. 10-RES-JB
    11. 8315
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a reason or cause for specific actions or situations

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate causation or reasons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oola
    -0.71
    oos
    -0.59
    =-=-=-=-=-=-=-=-
    -0.58
    rosso
    -0.56
     Phant
    -0.53
    dar
    -0.52
    anches
    -0.52
    rieve
    -0.51
     tatt
    -0.51
    aah
    -0.50
    POSITIVE LOGITS
     to
    1.09
     diligence
    0.94
     thereto
    0.87
     largely
    0.72
    lling
    0.72
     solely
    0.70
     primarily
    0.69
    itiz
    0.67
     mainly
    0.66
    llers
    0.65
    Activations Density 0.022%

    No Known Activations