© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 18013
    Prev
    Next
    INDEX
    Explanations

    references to the concept of the future or the word "future" itself

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "Future" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lee
    -0.83
    alties
    -0.78
    oaded
    -0.78
    alty
    -0.77
    aca
    -0.75
    mand
    -0.75
    arine
    -0.73
    orney
    -0.72
    hed
    -0.71
    otto
    -0.71
    POSITIVE LOGITS
     Future
    1.16
    Future
    1.07
    future
    0.97
     Directions
    0.84
     Generations
    0.83
     pregn
    0.82
     generations
    0.78
     Struggle
    0.77
    oday
    0.76
     Prospect
    0.74
    Activations Density 0.007%

    No Known Activations