© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 2053
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences emphasizing a strong emotional impact, often with positive connotations

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the word "such," indicating a focus on expressing significance or intensity

    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
    ntil
    -0.99
    ©¶æ
    -0.76
     Murd
    -0.75
    doctor
    -0.74
    iliate
    -0.73
    achus
    -0.71
    iliation
    -0.70
    achev
    -0.69
    kson
    -0.69
    oil
    -0.69
    POSITIVE LOGITS
    ities
    0.75
    liness
    0.75
     mundane
    0.72
     amazing
    0.70
     wonderful
    0.70
     marvelous
    0.69
     magnificent
    0.69
     exquisite
    0.68
     phenomenal
    0.68
     incredible
    0.68
    Activations Density 0.040%

    No Known Activations