© 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. 6-RES-JB
    11. 3039
    Prev
    Next
    INDEX
    Explanations

    keywords related to computer programming, technology, and legal terms

    oai_token-act-pair · gpt-3.5-turbo

    specific technical or organizational terms and names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çĶ°
    -0.61
    ).[
    -0.56
    ]."
    -0.56
    ".[
    -0.54
    20439
    -0.53
    Reloaded
    -0.53
     sqor
    -0.52
    Albert
    -0.51
    .")
    -0.50
    angers
    -0.50
    POSITIVE LOGITS
    ibliography
    0.57
    achu
    0.50
     Defenders
    0.49
     frust
    0.48
    fu
    0.46
     Quan
    0.46
    idious
    0.46
     postings
    0.45
     mechanics
    0.45
     Gren
    0.45
    Activations Density 0.891%

    No Known Activations