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. 14009
    Prev
    Next
    INDEX
    Explanations

    specific entities, such as company names and legal terms, especially related to intellectual property

    oai_token-act-pair · gpt-3.5-turbo

    references to legal entities and cases

    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
    ggles
    -0.77
    ahime
    -0.68
    âĺĨ
    -0.67
    !/
    -0.67
    ulhu
    -0.67
    å§«
    -0.67
    enment
    -0.64
     Thrones
    -0.61
    abeth
    -0.61
    ieval
    -0.60
    POSITIVE LOGITS
     unlawfully
    0.89
     plaintiffs
    0.89
     plaintiff
    0.85
     defendants
    0.81
     petitioner
    0.80
     unlawful
    0.78
     appellant
    0.77
     misconduct
    0.76
     Plaint
    0.75
     solicit
    0.75
    Activations Density 1.219%

    No Known Activations