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. 9-RES-JB
    6. 181
    Prev
    Next
    INDEX
    Explanations

    information about who directed and wrote a film or TV show

    oai_token-act-pair · gpt-3.5-turbo

    information related to directors and writers of movies or shows

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    obyl
    -0.82
    Merit
    -0.74
     deterrence
    -0.74
    ndum
    -0.72
     deval
    -0.71
     snowball
    -0.71
    Impl
    -0.71
    angered
    -0.69
    ophen
    -0.68
     worthless
    -0.67
    POSITIVE LOGITS
     screenplay
    1.28
     Producer
    1.11
     cinem
    1.06
    Production
    1.06
    Produ
    1.03
     composer
    1.03
     Editing
    1.02
     vocals
    1.01
     producer
    1.00
     narration
    0.99
    Activations Density 0.549%

    No Known Activations