© 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. 2-RES-JB
    11. 11572
    Prev
    Next
    INDEX
    Explanations

    capitalized acronyms and proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of network or organization acronyms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hoff
    -0.91
    naires
    -0.80
    lake
    -0.80
    vier
    -0.77
    ments
    -0.77
    heimer
    -0.71
    culosis
    -0.71
    omics
    -0.71
    gart
    -0.71
     Pill
    -0.70
    POSITIVE LOGITS
     ABS
    1.15
     reluct
    1.11
     mathemat
    1.10
     unden
    1.09
     challeng
    0.89
     conclud
    0.88
     corrid
    0.88
    channelAvailability
    0.87
     conduc
    0.87
    CAN
    0.86
    Activations Density 0.016%

    No Known Activations