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. 4-RES-JB
    6. 23016
    Prev
    Next
    INDEX
    Explanations

    words related to a specific name: "Preet Bharara"

    oai_token-act-pair · gpt-3.5-turbo

    words related to legal terms and legal proceedings

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

    No Comments

    Negative Logits
     resil
    -0.76
    soDeliveryDate
    -0.71
    keye
    -0.64
    cano
    -0.64
    YS
    -0.62
    VALUE
    -0.61
     torch
    -0.60
     Heller
    -0.59
    uncle
    -0.59
    ç¥ŀ
    -0.58
    POSITIVE LOGITS
    ing
    1.11
    eering
    0.96
    reet
    0.95
    icator
    0.90
    aah
    0.83
    icative
    0.82
    ypes
    0.81
    atives
    0.80
    eem
    0.80
    icators
    0.79
    Activations Density 0.017%

    No Known Activations