© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 9065
    Prev
    Next
    INDEX
    Explanations

    instances where an object or person is "sitting/standing out there"

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "there."

    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
     CJ
    -0.84
     ±
    -0.65
     Kobe
    -0.59
     cups
    -0.59
     pound
    -0.59
     Armored
    -0.58
     Abrams
    -0.57
     Cum
    -0.57
    ONSORED
    -0.56
     Mecca
    -0.55
    POSITIVE LOGITS
    abouts
    1.55
    upon
    0.95
     guiActiveUn
    0.84
    ngth
    0.81
    ntil
    0.80
     tradem
    0.74
    comings
    0.74
    onian
    0.74
    geist
    0.73
    Sov
    0.72
    Activations Density 0.144%

    No Known Activations