© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 13607
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Future" in a context related to various topics like music, movies, and economy

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "Future" or future-oriented themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oaded
    -0.93
    lee
    -0.92
    alty
    -0.90
    alties
    -0.90
    otto
    -0.75
    orney
    -0.72
    Downloadha
    -0.71
    ishy
    -0.69
    ocal
    -0.68
    istine
    -0.66
    POSITIVE LOGITS
     Generations
    0.97
     generations
    0.92
     Future
    0.90
     Directions
    0.84
     Generation
    0.83
    oday
    0.82
    Future
    0.80
    future
    0.74
     Warfare
    0.73
     2050
    0.72
    Activations Density 0.018%

    No Known Activations