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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 21350
    Prev
    Next
    INDEX
    Explanations

    words related to assassins, Templars, and video game titles like "Assassin's Creed" and "The Witcher"

    oai_token-act-pair · gpt-3.5-turbo

    references to the Assassin's Creed video game series and related themes

    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
    zl
    -0.85
    itably
    -0.74
    rol
    -0.72
    bles
    -0.72
     Prob
    -0.71
    artney
    -0.70
    hovah
    -0.70
    bos
    -0.69
    esville
    -0.69
    lopp
    -0.68
    POSITIVE LOGITS
     Assassin
    0.99
     Assassins
    0.98
     assassin
    0.95
     assassins
    0.92
     Creed
    0.81
     Templ
    0.80
     Inquisition
    0.79
    assin
    0.77
     Templar
    0.75
     Corpse
    0.72
    Activations Density 0.019%

    No Known Activations