© 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. 0-RES-JB
    11. 8251
    Prev
    Next
    INDEX
    Explanations

    words related to false perceptions or misconceptions

    oai_token-act-pair · gpt-3.5-turbo

    references to illusions and impressions in perception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FK
    -0.65
    kb
    -0.62
     Codes
    -0.60
     Weeks
    -0.59
    ocene
    -0.59
     calibr
    -0.58
     Crimes
    -0.58
     Packs
    -0.57
     Ports
    -0.57
     Schedule
    -0.57
    POSITIVE LOGITS
     impression
    2.60
     illusion
    2.57
     sensation
    1.57
     slightest
    1.38
     illusions
    1.36
    illusion
    1.34
     misconception
    1.25
     appearance
    1.10
     perception
    1.10
     effect
    0.97
    Activations Density 0.021%

    No Known Activations