© 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. 0-RES-JB
    11. 2130
    Prev
    Next
    INDEX
    Explanations

    mentions of corporations and entities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of corporations and associated metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tracks
    -0.84
     Dynam
    -0.83
    Tea
    -0.77
     Dragonbound
    -0.75
     Appl
    -0.74
     Techniques
    -0.72
     Essential
    -0.71
    zl
    -0.71
    hner
    -0.70
     SIG
    -0.70
    POSITIVE LOGITS
     corporation
    2.37
     radius
    1.42
    illery
    1.08
     corp
    1.03
     forfe
    1.01
     forfeit
    0.89
     federation
    0.87
     forfeiture
    0.86
    ohn
    0.85
     vault
    0.84
    Activations Density 0.036%

    No Known Activations