© 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. 886
    Prev
    Next
    INDEX
    Explanations

    terms related to a broad overarching concept or entity, such as "umbrella groups" or agreements

    oai_token-act-pair · gpt-3.5-turbo

    the word "umbrella" and its variations, indicating the concept of overarching themes or categories

    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
    avery
    -0.84
    nesota
    -0.80
    onew
    -0.76
    ogan
    -0.75
    anooga
    -0.70
    versions
    -0.70
    awar
    -0.70
    Comments
    -0.68
    entanyl
    -0.67
    esters
    -0.67
    POSITIVE LOGITS
     umbrella
    1.16
     umb
    1.05
    vine
    0.81
     poles
    0.78
     wip
    0.77
     blanket
    0.74
     cord
    0.72
    reon
    0.70
    izon
    0.69
    tip
    0.68
    Activations Density 0.007%

    No Known Activations