© 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. 9-RES-JB
    11. 17344
    Prev
    Next
    INDEX
    Explanations

    references to legal or formal documents

    oai_token-act-pair · gpt-3.5-turbo

    references to legal documents and records

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Interstitial
    -0.95
    Õ
    -0.84
    culosis
    -0.78
    iasis
    -0.71
    agonist
    -0.70
    odor
    -0.70
    osi
    -0.66
    phas
    -0.66
    atism
    -0.66
    atos
    -0.65
    POSITIVE LOGITS
     obtained
    1.11
     declass
    1.04
     leaked
    1.02
     unearthed
    1.01
     accessed
    1.01
     reviewed
    0.97
     reveal
    0.95
     filed
    0.94
     pertaining
    0.92
     retrieved
    0.91
    Activations Density 0.118%

    No Known Activations