© 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. 10190
    Prev
    Next
    INDEX
    Explanations

    words related to actions or processes involving significant change or improvement

    oai_token-act-pair · gpt-3.5-turbo

    words related to ceremonies and commemorations

    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
     statically
    -0.70
     criminals
    -0.67
     restraining
    -0.65
     criminal
    -0.64
     names
    -0.62
     hamstring
    -0.61
     chang
    -0.60
     shack
    -0.58
     sid
    -0.57
     Bench
    -0.57
    POSITIVE LOGITS
    oration
    4.35
    orate
    2.23
    orative
    1.79
    orer
    1.68
    orers
    1.61
    oring
    1.55
    ored
    1.49
    orable
    1.33
    ores
    1.23
    orship
    1.21
    Activations Density 0.012%

    No Known Activations