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. 10-RES-JB
    6. 2383
    Prev
    Next
    INDEX
    Explanations

    terms related to energy projects and pipelines

    oai_token-act-pair · gpt-3.5-turbo

    references to large-scale industrial projects and developments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Likes
    -0.84
     Anonymous
    -0.79
     handwriting
    -0.78
    ournal
    -0.77
     Zombies
    -0.74
    Anonymous
    -0.73
     Vegan
    -0.72
    xual
    -0.72
     furry
    -0.67
     roomm
    -0.67
    POSITIVE LOGITS
     pipeline
    1.48
     pipelines
    1.29
     refinery
    1.24
     rail
    1.23
     railway
    1.21
     dams
    1.20
     reactors
    1.18
     tanker
    1.18
     reactor
    1.17
     coal
    1.16
    Activations Density 0.469%

    No Known Activations