© 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. 690
    Prev
    Next
    INDEX
    Explanations

    terms related to stability, quality, and reliability

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to reliability and stability

    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
     DRAG
    -0.90
    ARC
    -0.79
    clerosis
    -0.75
    ynthesis
    -0.75
    ulhu
    -0.75
    ADS
    -0.75
    cart
    -0.75
    UME
    -0.73
    ILA
    -0.71
    stals
    -0.71
    POSITIVE LOGITS
    ly
    1.38
    ness
    1.23
    est
    1.03
    nesses
    0.99
     minded
    0.98
    ity
    0.97
    lly
    0.95
    hearted
    0.93
     manner
    0.88
    minded
    0.87
    Activations Density 0.255%

    No Known Activations