© 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. 1-RES-JB
    11. 14520
    Prev
    Next
    INDEX
    Explanations

    references to stories in various contexts, such as radio shows, television programs, news articles, and books

    oai_token-act-pair · gpt-3.5-turbo

    references to different types of stories and narrative content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ķ
    -0.80
    çĦ
    -0.75
    ×ŀ
    -0.70
    livion
    -0.68
    arb
    -0.67
     forestry
    -0.66
     labor
    -0.65
     protective
    -0.65
    ×Ķ
    -0.64
    ously
    -0.62
    POSITIVE LOGITS
     Tests
    1.08
     Rooms
    1.08
     Advice
    1.07
     Languages
    1.06
     Shots
    1.05
     Affect
    1.03
     Programs
    1.03
     Costs
    1.02
     Scores
    1.01
     Matters
    1.01
    Activations Density 0.127%

    No Known Activations