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. 3-RES-JB
    6. 19413
    Prev
    Next
    INDEX
    Explanations

    words related to law enforcement activities

    oai_token-act-pair · gpt-3.5-turbo

    gerunds and present participles formed from verbs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    behind
    -0.66
    omet
    -0.62
    spot
    -0.56
     vault
    -0.55
     ibn
    -0.54
     unc
    -0.53
     Chest
    -0.53
    cmp
    -0.53
    anya
    -0.53
     surviving
    -0.52
    POSITIVE LOGITS
    redients
    1.11
    LY
    0.83
    ulate
    0.80
    tons
    0.80
    inventoryQuantity
    0.78
    igate
    0.73
    aukee
    0.73
    encies
    0.71
    enance
    0.70
    GGGGGGGG
    0.69
    Activations Density 0.110%

    No Known Activations