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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 24298
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal proceedings and charges

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns and related references in a legal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     %%
    -0.78
    æĦ
    -0.74
    ISO
    -0.72
    Æ
    -0.72
     largeDownload
    -0.71
    qi
    -0.67
     [|
    -0.66
    igraph
    -0.66
    Reviewed
    -0.64
     Ichigo
    -0.64
    POSITIVE LOGITS
     accuser
    1.38
     attorney
    1.26
     arrest
    1.24
     attorneys
    1.22
     lawyer
    1.21
     arra
    1.20
     conviction
    1.19
     innocence
    1.16
     indictment
    1.14
     lawyers
    1.13
    Activations Density 0.145%

    No Known Activations