© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 15633
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Ark"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Ark" in various contexts

    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
    ãģ¦
    -0.84
    cussion
    -0.72
    perature
    -0.68
    TPS
    -0.68
    BOOK
    -0.67
    coat
    -0.66
     EFF
    -0.66
    GROUP
    -0.64
    ciation
    -0.64
    ãģŁ
    -0.64
    POSITIVE LOGITS
    ansas
    1.47
    wright
    1.07
     Encounter
    1.03
    angel
    1.02
    adelphia
    1.01
    esian
    0.95
    adia
    0.90
    arium
    0.88
    alis
    0.88
    anian
    0.88
    Activations Density 0.007%

    No Known Activations