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. 24259
    Prev
    Next
    INDEX
    Explanations

    names of fictional characters and real actors

    oai_token-act-pair · gpt-3.5-turbo

    significant characters and elements related to storytelling in movies and games

    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
    atories
    -0.88
    ETF
    -0.82
    ateurs
    -0.81
    mercial
    -0.79
    ourse
    -0.76
    insured
    -0.76
    Oregon
    -0.74
    SSL
    -0.73
    ERT
    -0.73
    unicip
    -0.73
    POSITIVE LOGITS
     humanoid
    1.11
     cameo
    1.05
     undead
    1.03
     voiced
    1.02
     backstory
    1.01
     badass
    1.00
     persona
    0.99
     avatar
    0.98
     NPCs
    0.97
     supernatural
    0.97
    Activations Density 0.877%

    No Known Activations