© 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. 10-RES-JB
    11. 11635
    Prev
    Next
    INDEX
    Explanations

    terms related to the combination of genetic material or inherent ability

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to individuality and collective experience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sidx
    -0.77
     nonetheless
    -0.69
    SourceFile
    -0.69
    Monitor
    -0.66
     respectively
    -0.64
    YES
    -0.63
    éŃĶ
    -0.62
    AZ
    -0.61
    STER
    -0.60
    onds
    -0.60
    POSITIVE LOGITS
     nor
    1.20
     anymore
    1.07
     necessarily
    1.04
     flashy
    0.95
     blindly
    0.89
     magically
    0.88
     mindless
    0.88
     overnight
    0.83
     gimmick
    0.83
     whim
    0.81
    Activations Density 0.732%

    No Known Activations