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. 5153
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Future" either related to the rapper or the concept of the future

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "future" and its various contexts and implications

    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
    alty
    -0.87
    alties
    -0.79
    lee
    -0.76
    oaded
    -0.73
     leve
    -0.71
     prick
    -0.69
    UCT
    -0.68
    Quantity
    -0.68
    cano
    -0.66
    ibu
    -0.64
    POSITIVE LOGITS
    izons
    0.95
    oday
    0.84
    future
    0.80
     Directions
    0.79
    uristic
    0.78
     Generations
    0.77
     generations
    0.75
     tense
    0.72
     scenarios
    0.71
     Future
    0.71
    Activations Density 0.057%

    No Known Activations