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. 808
    Prev
    Next
    INDEX
    Explanations

    phrases related to the term "Ghost"

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "Ghost" and related terms, indicating a focus on ghost-themed content

    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
    athe
    -0.78
    icably
    -0.67
    icable
    -0.67
     pse
    -0.67
     NCT
    -0.66
    pai
    -0.66
    1016
    -0.65
    verend
    -0.65
    OTHER
    -0.65
    enance
    -0.64
    POSITIVE LOGITS
    ertodd
    0.97
     Protocol
    0.96
    irlfriend
    0.93
     Squadron
    0.90
    regor
    0.89
    fighters
    0.86
    buster
    0.85
     Widow
    0.84
     Ship
    0.83
    anamo
    0.83
    Activations Density 0.025%

    No Known Activations