© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 3175
    Prev
    Next
    INDEX
    Explanations

    words related to abstract concepts or ideas, particularly illusions and delusions

    oai_token-act-pair · gpt-3.5-turbo

    references to illusions and delusions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Interstitial
    -0.85
    alez
    -0.67
    bid
    -0.65
    foreseen
    -0.64
     Selected
    -0.63
     Issues
    -0.62
    ded
    -0.61
    Discussion
    -0.61
    missions
    -0.61
    nan
    -0.61
    POSITIVE LOGITS
     illusion
    1.22
     Illusion
    1.01
     illusions
    0.98
     mir
    0.96
    istically
    0.91
    uration
    0.90
    ually
    0.90
    usional
    0.88
    ery
    0.87
    ary
    0.82
    Activations Density 0.014%

    No Known Activations