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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 8-RES-JB
    6. 20871
    Prev
    Next
    INDEX
    Explanations

    titles of movies, TV shows, and games

    oai_token-act-pair · gpt-3.5-turbo

    references to popular movies and television shows

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    istrate
    -0.83
     stakeholders
    -0.76
     listeners
    -0.75
     regulator
    -0.75
     knowledgeable
    -0.75
    verb
    -0.74
    agents
    -0.72
    irection
    -0.71
    informed
    -0.68
    igent
    -0.68
    POSITIVE LOGITS
    etc
    1.07
     etc
    1.02
    whatever
    0.89
     Guant
    0.84
     Rhodes
    0.80
     Odyssey
    0.80
     Notting
    0.78
     Baal
    0.77
     Libya
    0.77
     JFK
    0.77
    Activations Density 0.318%

    No Known Activations