© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 11110
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically related to specific entities such as organizations, people, and locations

    oai_token-act-pair · gpt-3.5-turbo

    references to specific names and terms associated with significant cultural or historical entities

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

    No Comments

    Negative Logits
    NetMessage
    -1.22
    76561
    -0.86
    idy
    -0.79
    irtual
    -0.78
    cknow
    -0.75
    cher
    -0.75
    leneck
    -0.74
    oms
    -0.74
    pped
    -0.74
    ops
    -0.73
    POSITIVE LOGITS
    ity
    0.81
     Falcon
    0.80
    theless
    0.73
     Caesar
    0.69
     Strauss
    0.68
     futures
    0.66
     GMT
    0.64
     Ca
    0.62
     Phelps
    0.62
     fal
    0.62
    Activations Density 0.032%

    No Known Activations