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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 18799
    Prev
    Next
    INDEX
    Explanations

    phrases related to event logistics and instructions

    oai_token-act-pair · gpt-3.5-turbo

    references to events and coordination of instructions

    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
    terday
    -0.75
    ĸļ
    -0.73
     slam
    -0.70
     cuts
    -0.69
     himself
    -0.68
    utics
    -0.67
     outweigh
    -0.66
    uca
    -0.65
     vir
    -0.65
     herself
    -0.65
    POSITIVE LOGITS
    Example
    1.19
    Disclaimer
    1.14
    NOTE
    1.10
    Additional
    1.09
    Important
    1.08
    Examples
    1.08
    Recommended
    1.06
    Please
    1.06
    Currently
    1.02
    Methods
    0.99
    Activations Density 0.580%

    No Known Activations