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. 15644
    Prev
    Next
    INDEX
    Explanations

    instructions or steps related to configuring or setting up various software components

    oai_token-act-pair · gpt-3.5-turbo

    instructions related to app development processes

    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
     crying
    -0.72
     Crosby
    -0.70
     laughing
    -0.69
     weeping
    -0.68
     taxp
    -0.68
     veiled
    -0.66
    hur
    -0.64
     traged
    -0.63
    hua
    -0.62
    living
    -0.62
    POSITIVE LOGITS
     initialize
    1.14
     configure
    0.99
    Setup
    0.92
     setup
    0.88
     calculate
    0.83
     manually
    0.83
     modify
    0.83
     generate
    0.81
     install
    0.80
     create
    0.79
    Activations Density 0.221%

    No Known Activations