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. 7-RES-JB
    6. 770
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Future" preceded by a specific identifier, such as "Back to the" or "Days of."

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "Future."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oaded
    -0.84
    quet
    -0.81
    alty
    -0.78
    cano
    -0.76
    lee
    -0.75
    alties
    -0.74
    otto
    -0.74
    ients
    -0.72
     leve
    -0.72
    ushing
    -0.69
    POSITIVE LOGITS
    izons
    0.83
     Generations
    0.78
    oday
    0.76
     Directions
    0.74
     Leap
    0.74
    future
    0.73
     Fut
    0.73
     Future
    0.70
     Direction
    0.69
    uristic
    0.69
    Activations Density 0.045%

    No Known Activations