© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 2660
    Prev
    Next
    INDEX
    Explanations

    phrases related to futuristic or sci-fi elements

    oai_token-act-pair · gpt-3.5-turbo

    specific phrases or references related to Pokémon and their characteristics

    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
    hene
    -0.85
     withdrawal
    -0.81
    utsche
    -0.79
    ividual
    -0.79
     privacy
    -0.76
     migrant
    -0.76
     candid
    -0.76
     migration
    -0.74
     quitting
    -0.73
     hourly
    -0.72
    POSITIVE LOGITS
    Contents
    1.71
    Trivia
    1.59
    Characters
    1.59
    pmwiki
    1.56
    Appearances
    1.40
    Gallery
    1.37
    Gameplay
    1.32
    Episode
    1.24
    Spoiler
    1.23
    Notes
    1.20
    Activations Density 0.338%

    No Known Activations