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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 12590
    Prev
    Next
    INDEX
    Explanations

    morphemes related to augmented reality (AR) and technology

    oai_token-act-pair · gpt-3.5-turbo

    references to "AR" and its various contexts, likely related to specific products or technologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hower
    -0.78
    ures
    -0.74
    hirt
    -0.66
     Mercury
    -0.65
     Petr
    -0.64
     Rollins
    -0.63
     Pelosi
    -0.63
    ornia
    -0.61
    tons
    -0.61
    bourg
    -0.60
    POSITIVE LOGITS
    ENA
    1.09
    RAY
    0.97
    OUND
    0.89
    senal
    0.88
    LY
    0.87
    RR
    0.83
    RL
    0.83
    ansas
    0.82
    ANGE
    0.82
    IZ
    0.82
    Activations Density 0.025%

    No Known Activations