© 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. 10-RES-JB
    11. 10057
    Prev
    Next
    INDEX
    Explanations

    other words and phrases related to interaction and relationships between individuals

    oai_token-act-pair · gpt-3.5-turbo

    interactions between entities or individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aroo
    -0.77
    wcs
    -0.67
    levard
    -0.65
    adier
    -0.65
    lot
    -0.63
    sic
    -0.63
    videos
    -0.62
    unction
    -0.62
    zx
    -0.61
    marine
    -0.61
    POSITIVE LOGITS
     each
    2.19
    each
    1.79
     Each
    1.52
     apiece
    1.50
    Each
    1.39
    selves
    0.83
     respectively
    0.82
     another
    0.81
     themselves
    0.80
     apart
    0.76
    Activations Density 0.478%

    No Known Activations