© 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. 8-RES-JB
    11. 7872
    Prev
    Next
    INDEX
    Explanations

    terms related to speech recognition

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various forms of recognition technologies

    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
    ewitness
    -0.86
    zl
    -0.80
    ghazi
    -0.78
    birth
    -0.74
    ISH
    -0.72
    ogie
    -0.70
    cci
    -0.70
    ild
    -0.70
    zynski
    -0.69
    zn
    -0.69
    POSITIVE LOGITS
     algorithms
    1.19
     capabilities
    1.18
     capability
    1.12
     technologies
    1.10
     mechanisms
    1.09
     systems
    1.08
     devices
    1.04
     technology
    1.03
     software
    1.02
     tools
    1.02
    Activations Density 0.241%

    No Known Activations