© 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. 2293
    Prev
    Next
    INDEX
    Explanations

    phrases related to making decisions or giving advice

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of a specific character sequence or symbol

    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
     literacy
    -0.71
     pyramid
    -0.69
     lodging
    -0.67
     kicker
    -0.67
     recycling
    -0.64
     prostitutes
    -0.64
     opportunities
    -0.63
     Shelter
    -0.62
     strat
    -0.62
     cellphone
    -0.62
    POSITIVE LOGITS
    ï¸ı
    1.48
    âĶĢâĶĢâĶĢâĶĢ
    1.19
    ¯¯
    1.18
    £
    1.05
    âĻ
    1.03
    ¯
    1.00
    ¢
    0.97
    ï¸
    0.96
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    0.96
    âĶĢ
    0.94
    Activations Density 0.247%

    No Known Activations