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. 2-RES-JB
    6. 17959
    Prev
    Next
    INDEX
    Explanations

    words related to movie titles and specific terms within movie plots

    oai_token-act-pair · gpt-3.5-turbo

    quoted phrases, particularly from film and literature titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anmar
    -0.75
    itably
    -0.75
    idge
    -0.69
     dispers
    -0.67
    ogene
    -0.63
     sow
    -0.62
    itionally
    -0.62
    bread
    -0.62
     vagina
    -0.62
     CLSID
    -0.61
    POSITIVE LOGITS
    »
    1.24
     «
    1.01
    «
    0.89
     »
    0.89
    ï¸ı
    0.83
    tal
    0.79
    CLASSIFIED
    0.79
    Prev
    0.77
    yu
    0.74
    âĢł
    0.73
    Activations Density 0.006%

    No Known Activations