Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 24307
    Prev
    Next
    INDEX
    Explanations

    references to speculative and futuristic settings or scenarios

    oai_token-act-pair · gpt-3.5-turbo

    themes related to alternate realities and dystopian futures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     actionGroup
    -0.92
    drivers
    -0.79
    Boost
    -0.78
    rators
    -0.76
    orsi
    -0.76
    links
    -0.74
    anches
    -0.72
    phies
    -0.71
     Cosponsors
    -0.71
    cu
    -0.70
    POSITIVE LOGITS
     world
    1.71
     universe
    1.65
     dystop
    1.61
     paradise
    1.52
     worlds
    1.41
    world
    1.38
     dystopian
    1.36
     planet
    1.31
     realm
    1.28
     afterlife
    1.28
    Activations Density 0.450%

    No Known Activations