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. 14506
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Rel" followed by a number indicating its level of relevance or importance

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "real" or "related" entities, predominantly in a specific context

    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
    HAEL
    -0.95
    enegger
    -0.69
    avorite
    -0.67
    BOX
    -0.66
    thur
    -0.65
    schild
    -0.65
    manship
    -0.63
    terday
    -0.63
    gerald
    -0.63
    ãģ®ç
    -0.63
    POSITIVE LOGITS
    igion
    1.26
    iance
    1.24
    iever
    1.21
    iability
    1.18
    iable
    1.10
    atively
    1.05
    inqu
    1.01
    ieved
    1.00
    ievers
    1.00
    ativity
    1.00
    Activations Density 0.013%

    No Known Activations