© 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. 3-RES-JB
    11. 23549
    Prev
    Next
    INDEX
    Explanations

    mentions of specific entities or concepts related to various topics, such as politics, economics, technology, and healthcare

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to military and governmental organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .''
    -0.43
    ".[
    -0.43
     behalf
    -0.42
    Common
    -0.42
    Interstitial
    -0.42
    î
    -0.41
    tnc
    -0.40
     hers
    -0.39
    }.
    -0.39
    $.
    -0.39
    POSITIVE LOGITS
     meanwhile
    0.49
     however
    0.46
     sprang
    0.42
     historians
    0.42
     consists
    0.42
     consisted
    0.42
     moreover
    0.41
    surprisingly
    0.41
     grew
    0.41
     extends
    0.41
    Activations Density 3.006%

    No Known Activations