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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 16073
    Prev
    Next
    INDEX
    Explanations

    ideas, themes, and concepts related to science fiction and fantasy

    oai_token-act-pair · gpt-3.5-turbo

    references to science fiction and fantasy themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SHARE
    -0.89
    çĦ
    -0.87
    otte
    -0.83
    umm
    -0.79
    aved
    -0.71
    lease
    -0.71
     snipp
    -0.70
    rien
    -0.69
    iris
    -0.69
    rael
    -0.69
    POSITIVE LOGITS
     thriller
    1.13
     novels
    1.02
     fiction
    1.00
     trope
    0.99
    ampunk
    0.96
     dystop
    0.94
     sequel
    0.94
     adventure
    0.89
    ishly
    0.89
     Fiction
    0.89
    Activations Density 0.050%

    No Known Activations