© 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. 11-RES-JB
    11. 5142
    Prev
    Next
    INDEX
    Explanations

    names and proper nouns related to individuals or locations

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns related to Catalonia and individuals associated with it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ly
    -0.91
    manship
    -0.87
    ABLE
    -0.79
    FUL
    -0.77
    strap
    -0.70
    liest
    -0.67
    fully
    -0.66
    fulness
    -0.65
    âĸ¬
    -0.65
    STEM
    -0.65
    POSITIVE LOGITS
    onse
    1.27
    onso
    1.25
    ernand
    1.05
    atch
    0.98
    abet
    0.95
    enary
    0.94
    ons
    0.94
    inating
    0.94
    ain
    0.93
    inated
    0.93
    Activations Density 0.125%

    No Known Activations