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. 0-RES-JB
    6. 24433
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific gaming series, "Fallout"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the "Fallout" video game series

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¶
    -0.67
    isher
    -0.66
     accountable
    -0.65
    ools
    -0.62
    her
    -0.62
     instructed
    -0.62
     iv
    -0.61
     bus
    -0.61
     rem
    -0.61
    Ģ
    -0.61
    POSITIVE LOGITS
     Fallout
    3.15
     Wasteland
    1.26
     Borderlands
    1.25
     Diablo
    1.01
     Ranger
    1.00
     XCOM
    0.99
     Oblivion
    0.98
     Bethesda
    0.96
    pmwiki
    0.94
     Pathfinder
    0.92
    Activations Density 0.006%

    No Known Activations