© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 17420
    Prev
    Next
    INDEX
    Explanations

    phrases related to sharing information or being informed about a situation

    oai_token-act-pair · gpt-3.5-turbo

    structured phrases related to communication and statements made by individuals

    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
    Cub
    -0.84
     Hydra
    -0.74
     Atlas
    -0.71
     âĸĪ
    -0.65
    ô
    -0.64
     Myr
    -0.64
     Beacon
    -0.64
     Cuban
    -0.62
     Becky
    -0.62
    Weiss
    -0.62
    POSITIVE LOGITS
    jriwal
    1.06
     Kejriwal
    1.03
     Maharashtra
    1.02
     learnt
    1.01
     Punjab
    0.99
     Lok
    0.99
     Kumar
    0.99
     Gujarat
    0.99
     BJP
    0.98
     Sharma
    0.98
    Activations Density 0.458%

    No Known Activations