© 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. 11-RES-JB
    11. 20655
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to storytelling and recounting events, particularly involving actions and dialogue between people

    oai_token-act-pair · gpt-3.5-turbo

    instances of interpersonal relationships and their complexities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     util
    -0.92
    Firstly
    -0.81
    yip
    -0.80
     advantageous
    -0.73
     advoc
    -0.72
     promoting
    -0.72
    udos
    -0.71
     Vs
    -0.70
     opponent
    -0.70
     opposing
    -0.69
    POSITIVE LOGITS
    âĢ¢âĢ¢
    1.24
    âĢ
    1.09
     âĢ
    0.99
     vanished
    0.92
    âĢł
    0.90
    —"
    0.89
    ··
    0.87
     remembers
    0.85
     drifted
    0.85
     haun
    0.83
    Activations Density 0.932%

    No Known Activations