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

    Neuronpedia

    APICircuit 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. 1-RES-JB
    6. 9733
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal proceedings and authority figures such as judges presiding over cases

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "presided" and its variations in relation to judicial or authoritative contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ted
    -0.79
    ting
    -0.70
    amaz
    -0.69
    fts
    -0.66
    obo
    -0.66
    rav
    -0.65
    WB
    -0.65
    CDC
    -0.64
    ggies
    -0.64
    requ
    -0.64
    POSITIVE LOGITS
     presided
    1.53
     presiding
    1.18
    ĸļ
    0.84
     overse
    0.81
     offic
    0.77
     conduc
    0.75
     oversaw
    0.72
     appointing
    0.72
    ominated
    0.70
     administ
    0.70
    Activations Density 0.010%

    No Known Activations