© 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. 8-RES-JB
    11. 8493
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or processes occurring with a significant impact or outcome

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to processes and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Develop
    -0.64
     moreover
    -0.59
     Attributes
    -0.56
     Nurs
    -0.56
     Definitions
    -0.55
     Converted
    -0.55
     alot
    -0.54
     Concept
    -0.54
     Apart
    -0.54
     Physical
    -0.52
    POSITIVE LOGITS
    ãĤ©
    0.72
    kj
    0.69
    20439
    0.65
    ãĤ´ãĥ³
    0.65
    liest
    0.65
    *.
    0.63
    lease
    0.62
    ottesville
    0.62
    epad
    0.61
    stretched
    0.61
    Activations Density 0.787%

    No Known Activations