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. 10-RES-JB
    6. 15140
    Prev
    Next
    INDEX
    Explanations

    words related to valuable items or precious objects

    oai_token-act-pair · gpt-3.5-turbo

    elements related to theft and valuable items

    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
    axis
    -0.79
     Reporting
    -0.78
     NCT
    -0.77
    VPN
    -0.75
    params
    -0.74
    voice
    -0.72
     thrott
    -0.72
    SPA
    -0.72
    iannopoulos
    -0.71
    renheit
    -0.71
    POSITIVE LOGITS
     priceless
    1.60
     treasures
    1.56
     souven
    1.47
     jewelry
    1.42
     collector
    1.40
    abilia
    1.39
     treasure
    1.37
     collectors
    1.37
     valued
    1.36
     sentimental
    1.36
    Activations Density 0.734%

    No Known Activations