© 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. 7-RES-JB
    11. 23561
    Prev
    Next
    INDEX
    Explanations

    phrases related to beliefs, descriptions, and assumptions about certain topics or entities

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express common beliefs or perceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aleb
    -0.62
     Donkey
    -0.60
     disg
    -0.60
     Hungry
    -0.60
     Bravo
    -0.58
     Kl
    -0.58
    alos
    -0.57
     VG
    -0.57
     Competition
    -0.56
     Sierra
    -0.56
    POSITIVE LOGITS
    isSpecialOrderable
    0.78
    ت
    0.75
     pegged
    0.71
    س
    0.70
    hack
    0.68
    inet
    0.68
    ypes
    0.67
    idable
    0.66
    à¨
    0.66
     derog
    0.66
    Activations Density 0.159%

    No Known Activations