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. 11-RES-JB
    6. 18347
    Prev
    Next
    INDEX
    Explanations

    references to the historical relic known as the "Bird's Head Hagaddah."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ad" or its variations related to advertisement or promotional content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     slack
    -0.66
     backwards
    -0.62
     Canaver
    -0.58
     silence
    -0.58
     Manit
    -0.57
     sterling
    -0.56
     classified
    -0.56
     Lovecraft
    -0.56
     CSI
    -0.55
     corp
    -0.55
    POSITIVE LOGITS
    urai
    1.29
    visor
    1.20
    venture
    1.18
    onna
    1.14
    visors
    1.12
    illac
    1.11
    rill
    1.10
    ventures
    1.09
    aily
    1.07
    elta
    1.06
    Activations Density 0.054%

    No Known Activations