© 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. 3-RES-JB
    11. 14740
    Prev
    Next
    INDEX
    Explanations

    adjectives related to invisibility or hiddenness

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of invisibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ortment
    -0.81
    xit
    -0.76
    ership
    -0.75
    ourses
    -0.75
    owder
    -0.74
    olitan
    -0.74
    inion
    -0.73
    nia
    -0.73
    andals
    -0.73
    aeper
    -0.73
    POSITIVE LOGITS
     invisible
    0.97
     invis
    0.93
     volcano
    0.85
     Invisible
    0.78
     unseen
    0.78
     phantom
    0.75
     disco
    0.74
     invincible
    0.72
    worm
    0.72
     disappear
    0.72
    Activations Density 0.012%

    No Known Activations