© 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. 4-RES-JB
    11. 7508
    Prev
    Next
    INDEX
    Explanations

    personal information data points like age, experience, college, location, and time frames

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and measurements associated with time, age, and experiences

    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
    xual
    -0.72
     wrapped
    -0.64
    ĸļ
    -0.63
     directly
    -0.62
     buggy
    -0.59
     thereto
    -0.59
     lect
    -0.59
     stomp
    -0.59
     blindly
    -0.58
     ammon
    -0.58
    POSITIVE LOGITS
    Rating
    0.83
    Minimum
    0.81
    Tags
    0.80
    Filename
    0.79
    Password
    0.78
    Sensor
    0.78
    Project
    0.77
    Recommended
    0.77
    Posts
    0.77
    Package
    0.75
    Activations Density 0.308%

    No Known Activations