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. 9912
    Prev
    Next
    INDEX
    Explanations

    keywords related to interaction with others

    oai_token-act-pair · gpt-3.5-turbo

    references to other individuals or groups in the context of interactions and behaviors

    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
    Accessory
    -0.72
    itation
    -0.71
    ihara
    -0.65
    owship
    -0.61
    obar
    -0.60
    ocracy
    -0.60
     Hulk
    -0.60
    oho
    -0.59
     Warlock
    -0.59
     centerpiece
    -0.59
    POSITIVE LOGITS
    cius
    0.88
    ĸļ
    0.83
    ystem
    0.79
    ngth
    0.79
     describ
    0.78
     indo
    0.76
    paces
    0.75
    miah
    0.75
     behavi
    0.74
    cript
    0.73
    Activations Density 0.032%

    No Known Activations