© 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. 7558
    Prev
    Next
    INDEX
    Explanations

    documents or sources that contain specific types of content (videos, memos, articles, speeches, books, reports, letters)

    oai_token-act-pair · gpt-3.5-turbo

    references to specific forms of communication

    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
    ccording
    -0.74
    ecause
    -0.69
    avorite
    -0.66
    ancial
    -0.65
    relative
    -0.63
    orkshire
    -0.62
     stray
    -0.59
     forbid
    -0.59
    Aid
    -0.59
    inx
    -0.59
    POSITIVE LOGITS
    quad
    0.74
     FI
    0.67
     Volks
    0.66
     acknowled
    0.66
    antry
    0.65
     circles
    0.63
     hamm
    0.61
     enclosure
    0.60
     mode
    0.60
    ixties
    0.60
    Activations Density 0.242%

    No Known Activations