© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 13822
    Prev
    Next
    INDEX
    Explanations

    financial and technical terms

    oai_token-act-pair · gpt-3.5-turbo

    references to diverse groups and their interactions within systems

    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
    Anyway
    -0.98
     Stupid
    -0.98
     crap
    -0.97
     anyway
    -0.95
     Nope
    -0.94
     forgetting
    -0.90
    Yep
    -0.89
     Anyway
    -0.86
     idiots
    -0.85
    shit
    -0.84
    POSITIVE LOGITS
     embody
    1.28
     contribute
    1.26
     characterize
    1.25
     enhance
    1.24
     facilitate
    1.22
     provide
    1.22
     propose
    1.21
     engage
    1.20
     incorporate
    1.18
     evaluate
    1.17
    Activations Density 0.643%

    No Known Activations