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. 3-RES-JB
    6. 8418
    Prev
    Next
    INDEX
    Explanations

    mentions of the supernatural entity "ghost"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "ghost."

    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
    erity
    -0.88
    undred
    -0.74
    unes
    -0.73
    tics
    -0.71
    arta
    -0.68
    ibaba
    -0.68
    inion
    -0.67
    thritis
    -0.67
    UTERS
    -0.66
    oulos
    -0.66
    POSITIVE LOGITS
    busters
    1.08
    ghost
    0.97
    writer
    0.95
    writing
    0.94
    buster
    0.89
     haunting
    0.83
    written
    0.83
    glass
    0.81
    Haunted
    0.79
    door
    0.78
    Activations Density 0.016%

    No Known Activations