© 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. 7-RES-JB
    6. 12584
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing specific importance, often using words like "above all" or "more than anything"

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the word "all" or variations of it in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MpServer
    -0.66
    NY
    -0.62
    gee
    -0.61
    las
    -0.59
     Cosponsors
    -0.58
    arbon
    -0.58
     UCHIJ
    -0.58
     quar
    -0.57
    Uh
    -0.56
    nell
    -0.56
    POSITIVE LOGITS
     else
    1.10
    vention
    0.68
     Flask
    0.67
    Ùħ
    0.65
    orem
    0.63
    Else
    0.63
    THING
    0.63
    س
    0.63
    conservancy
    0.62
     occasions
    0.62
    Activations Density 0.041%

    No Known Activations