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. 10080
    Prev
    Next
    INDEX
    Explanations

    adjectives related to dream-like, imaginative, and bizarre experiences

    oai_token-act-pair · gpt-3.5-turbo

    themes and concepts related to the surreal and fantastical

    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
    PLE
    -0.64
    IELD
    -0.64
     PAY
    -0.63
    BY
    -0.63
    ORD
    -0.63
     Caesar
    -0.63
    EVA
    -0.62
     Thor
    -0.62
    âĸ¬
    -0.62
    bury
    -0.62
    POSITIVE LOGITS
    ism
    2.24
    ists
    2.18
    istic
    2.14
    ist
    2.11
    istically
    2.04
    isms
    1.64
    istical
    1.64
    ized
    1.45
    ISM
    1.43
    ization
    1.41
    Activations Density 0.051%

    No Known Activations