© 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. 10730
    Prev
    Next
    INDEX
    Explanations

    terms with the prefix "non-" followed by words related to entities or terms

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate exceptions or specific classifications, particularly the prefix "non-"

    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
     Brus
    -0.81
     Bam
    -0.78
     Grill
    -0.78
     Tycoon
    -0.76
     Ney
    -0.74
     Led
    -0.73
     Wonderland
    -0.73
     Arrows
    -0.73
     Oaks
    -0.73
     Maze
    -0.72
    POSITIVE LOGITS
    existent
    1.87
    profit
    1.65
    traditional
    1.54
    violent
    1.48
    linear
    1.46
    partisan
    1.44
    profits
    1.43
    governmental
    1.42
    lethal
    1.41
    resident
    1.41
    Activations Density 0.029%

    No Known Activations