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. 8-RES-JB
    6. 21222
    Prev
    Next
    INDEX
    Explanations

    terms related to programs, projects, and initiatives

    oai_token-act-pair · gpt-3.5-turbo

    references to government programs and initiatives

    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
     hardness
    -0.79
     alloy
    -0.75
     keyboards
    -0.72
     accents
    -0.71
     keyboard
    -0.69
     Temper
    -0.69
    izu
    -0.68
    erald
    -0.68
     Metallic
    -0.67
     flakes
    -0.67
    POSITIVE LOGITS
     funded
    1.26
    funded
    1.16
     undertaken
    1.06
     operated
    1.05
     staffed
    1.02
    ONSORED
    1.02
     overseen
    1.01
     financed
    1.01
     funding
    1.01
     nationwide
    0.99
    Activations Density 0.649%

    No Known Activations