© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 3-RES-JB
    11. 5687
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computer systems

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of systems, particularly computer and technology-related systems

    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
    liest
    -0.86
    æĢ
    -0.82
    lier
    -0.78
    bow
    -0.76
    à
    -0.73
    ish
    -0.72
    ished
    -0.72
    ãĥĥ
    -0.72
    iversary
    -0.71
    onga
    -0.70
    POSITIVE LOGITS
    etting
    1.19
     systems
    1.15
    afety
    1.08
    pace
    1.00
     integ
    1.00
    ensical
    0.99
    mith
    0.96
    etter
    0.96
     architectures
    0.93
    peak
    0.92
    Activations Density 0.016%

    No Known Activations