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. 8-RES-JB
    6. 9697
    Prev
    Next
    INDEX
    Explanations

    specific references to media content

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of roles and games, particularly in a contextual or metaphorical sense

    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
    ablishment
    -0.81
    Grab
    -0.71
     Publishers
    -0.65
    eele
    -0.64
     landfall
    -0.64
    arching
    -0.62
    qqa
    -0.62
    TOP
    -0.60
    ousse
    -0.60
    ortium
    -0.60
    POSITIVE LOGITS
     Mahjong
    0.90
     piano
    0.80
     role
    0.76
     drums
    0.75
     poker
    0.73
     roles
    0.71
     games
    0.71
     game
    0.69
    estyles
    0.68
     Piano
    0.67
    Activations Density 0.161%

    No Known Activations