© 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. 8-RES-JB
    11. 5114
    Prev
    Next
    INDEX
    Explanations

    mentions of software programs or tools

    oai_token-act-pair · gpt-3.5-turbo

    instances of software and tools used for digital processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bernatorial
    -0.81
    ghazi
    -0.78
    emale
    -0.74
    ategories
    -0.70
    ultural
    -0.70
     Restaur
    -0.69
    lesiastical
    -0.69
    angered
    -0.68
    Merit
    -0.68
    女
    -0.67
    POSITIVE LOGITS
     technique
    0.90
     plugin
    0.82
     notation
    0.80
     algorithm
    0.78
     microscope
    0.78
     scanner
    0.76
     combination
    0.76
     emulator
    0.75
     supplemented
    0.75
     simulator
    0.74
    Activations Density 0.565%

    No Known Activations