© 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. 11-RES-JB
    11. 22418
    Prev
    Next
    INDEX
    Explanations

    references to technological specifications such as battery size, screen dimensions, and connectivity options

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate specifications or features of gadgets and electronics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AIDS
    -0.82
    insk
    -0.73
     advis
    -0.72
    immigration
    -0.70
    ographs
    -0.70
    analysis
    -0.69
    Eastern
    -0.69
    anism
    -0.67
    NP
    -0.67
    Angel
    -0.66
    POSITIVE LOGITS
     touchscreen
    1.05
     removable
    0.99
     plethora
    0.95
     whopping
    0.94
     sleek
    0.93
     Snapdragon
    0.92
     multitude
    0.90
     joystick
    0.88
     decent
    0.87
     cheap
    0.87
    Activations Density 0.173%

    No Known Activations