© 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. 7-RES-JB
    11. 4377
    Prev
    Next
    INDEX
    Explanations

    words relating to specific locations or countries

    oai_token-act-pair · gpt-3.5-turbo

    specific geographical locations, biological terms, and references to agricultural and trade-related concepts

    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
    needed
    -0.71
    Adapt
    -0.62
     challeng
    -0.61
     awa
    -0.59
    ignty
    -0.59
     accordingly
    -0.58
     antidote
    -0.56
    tem
    -0.55
    çİĭ
    -0.55
     sizeof
    -0.54
    POSITIVE LOGITS
     standpoint
    1.38
     onwards
    1.22
     vantage
    1.01
     onward
    0.99
     perspective
    0.97
     sources
    0.90
    ratch
    0.80
     Shutterstock
    0.77
     outset
    0.75
     viewpoint
    0.73
    Activations Density 0.793%

    No Known Activations