© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 856
    Prev
    Next
    INDEX
    Explanations

    mentions of augmented reality technologies

    oai_token-act-pair · gpt-3.5-turbo

    terms related to augmented reality and its applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    acht
    -0.77
    isters
    -0.75
    issue
    -0.70
     Pelosi
    -0.69
    士
    -0.69
    cha
    -0.69
    Fed
    -0.68
     Kills
    -0.67
    ests
    -0.67
    sol
    -0.65
    POSITIVE LOGITS
     augmented
    1.30
    mented
    1.09
    mentation
    0.93
     augment
    0.90
    intosh
    0.79
     reality
    0.78
    ĸļ
    0.77
     automation
    0.75
    ovember
    0.75
    ments
    0.74
    Activations Density 0.004%

    No Known Activations