© 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. 10-RES-JB
    11. 24066
    Prev
    Next
    INDEX
    Explanations

    code snippets related to the Taboola advertising platform

    oai_token-act-pair · gpt-3.5-turbo

    elements related to advertising and content placement code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aughs
    -0.79
    orem
    -0.72
    ingers
    -0.72
    escription
    -0.71
    alach
    -0.70
    touch
    -0.69
    ĺħ
    -0.69
    yip
    -0.68
    oday
    -0.68
    eport
    -0.68
    POSITIVE LOGITS
    wcsstore
    1.08
    channelAvailability
    0.78
    ItemImage
    0.78
    null
    0.75
    ãģ®ç
    0.74
    ":[{"
    0.73
    taboola
    0.72
     isEnabled
    0.70
    è¦
    0.69
    ãģ®æ
    0.67
    Activations Density 0.024%

    No Known Activations