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. 7-RES-JB
    6. 17066
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to science fiction or fantasy concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to specific fictional franchises or universes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ahoo
    -0.84
    perature
    -0.78
    ney
    -0.78
    oshop
    -0.77
    enegger
    -0.74
    ographically
    -0.74
    ahon
    -0.73
    irsch
    -0.73
    estern
    -0.73
    say
    -0.73
    POSITIVE LOGITS
     Reborn
    1.07
     Rising
    1.06
     Centauri
    1.03
     Squadron
    1.01
     Warfare
    0.94
     Crusade
    0.93
     Breaker
    0.91
     Wars
    0.89
     Trooper
    0.88
     Tactics
    0.87
    Activations Density 0.227%

    No Known Activations