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. 6-RES-JB
    6. 21355
    Prev
    Next
    INDEX
    Explanations

    instances of objects being physically connected to something else

    oai_token-act-pair · gpt-3.5-turbo

    connections and interactions among devices and networks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ô
    -0.81
    URES
    -0.77
    amaz
    -0.75
    gor
    -0.68
    hiro
    -0.67
    ouri
    -0.67
    vier
    -0.67
    perse
    -0.66
    æľ
    -0.66
     divor
    -0.65
    POSITIVE LOGITS
     rest
    0.85
     underside
    0.82
     existing
    0.80
     nearest
    0.80
     pree
    0.80
     mainland
    0.79
     motherboard
    0.78
     nucleus
    0.74
     bloodstream
    0.71
     mast
    0.69
    Activations Density 0.435%

    No Known Activations