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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7-RES-JB
    11. 21262
    Prev
    Next
    INDEX
    Explanations

    scientific and technical terms related to biology and chemistry

    oai_token-act-pair · gpt-3.5-turbo

    descriptors of physical attributes or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     outsourcing
    -0.82
    CPU
    -0.75
     Computing
    -0.73
    Zero
    -0.73
    Asset
    -0.72
    AI
    -0.72
     Accountability
    -0.71
    DCS
    -0.71
     PSU
    -0.71
     commitments
    -0.71
    POSITIVE LOGITS
     specimens
    0.97
     dorsal
    0.94
     elong
    0.93
     basal
    0.93
    morph
    0.90
     pollen
    0.89
     larvae
    0.88
     glands
    0.87
     species
    0.87
     specimen
    0.87
    Activations Density 0.855%

    No Known Activations