© 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. 8-RES-JB
    11. 3287
    Prev
    Next
    INDEX
    Explanations

    phrases related to subscribing or opting out

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of time and timing-related phrases

    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
    avorite
    -0.79
    ards
    -0.68
    uned
    -0.64
    ging
    -0.64
    arded
    -0.64
    iar
    -0.64
    ateur
    -0.64
    agra
    -0.61
    eur
    -0.61
    uno
    -0.60
    POSITIVE LOGITS
    zone
    0.91
    aneously
    0.83
    lot
    0.78
    cale
    0.75
    frames
    0.74
     thereafter
    0.72
     throughout
    0.71
     intervals
    0.71
     during
    0.69
     periods
    0.67
    Activations Density 0.047%

    No Known Activations