Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 13346
    Prev
    Next
    INDEX
    Explanations

    references to supernatural entities or phenomena, especially ghosts

    oai_token-act-pair · gpt-3.5-turbo

    references to ghosts and ghostly themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erity
    -0.89
    tics
    -0.73
    unes
    -0.73
    undred
    -0.70
    arta
    -0.67
     NAD
    -0.67
    ibaba
    -0.65
    onsense
    -0.64
    ãĥ¼ãĥ³
    -0.64
    avez
    -0.64
    POSITIVE LOGITS
    busters
    1.07
    ghost
    0.96
    buster
    0.89
    writing
    0.89
    writer
    0.86
    glass
    0.84
     suspic
    0.83
     haunting
    0.82
     ghost
    0.81
     Chaser
    0.79
    Activations Density 0.012%

    No Known Activations