© 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. 1-RES-JB
    11. 3361
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Ghost"

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "Ghost" and its associated terms, particularly in relation to media and entertainment

    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
    enegger
    -0.76
    UTC
    -0.75
    1016
    -0.72
    unes
    -0.72
    utherford
    -0.71
    thritis
    -0.70
    ublic
    -0.68
    ewski
    -0.68
     repeat
    -0.68
    oÄŁ
    -0.67
    POSITIVE LOGITS
     Ghost
    1.07
    buster
    1.01
    busters
    0.99
    ertodd
    0.98
    Ghost
    0.94
    ghost
    0.92
    door
    0.88
     Bunny
    0.86
     Chaser
    0.84
     Ghosts
    0.80
    Activations Density 0.010%

    No Known Activations