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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 1749
    Prev
    Next
    INDEX
    Explanations

    words related to intellectual property or actions related to claiming ownership

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "ip."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EntityItem
    -0.90
     Dying
    -0.77
    é¾
    -0.74
    DEV
    -0.74
    DERR
    -0.73
    ÙIJ
    -0.72
    Ùİ
    -0.72
    âĸ¬
    -0.70
    ufact
    -0.68
    BIP
    -0.68
    POSITIVE LOGITS
    artisan
    1.32
    otent
    1.24
    osit
    1.14
    ublic
    1.08
    ulse
    1.02
    rompt
    1.02
    resent
    1.01
    inion
    1.01
    rint
    1.01
    olitan
    1.00
    Activations Density 0.035%

    No Known Activations