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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 20540
    Prev
    Next
    INDEX
    Explanations

    words related to legal actions, such as "appeal" and "ruling."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal appeals

    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
    kson
    -0.78
    fters
    -0.66
    ãĤ¿
    -0.62
     Hots
    -0.62
    adata
    -0.62
    ifa
    -0.60
    FORE
    -0.59
    apy
    -0.58
    ipes
    -0.58
    shaw
    -0.58
    POSITIVE LOGITS
     against
    0.89
     court
    0.88
    against
    0.79
     tribunal
    0.77
    ĸļ
    0.77
     appeals
    0.75
    process
    0.72
     judge
    0.71
     courts
    0.71
    rators
    0.70
    Activations Density 0.036%

    No Known Activations