© 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. 12040
    Prev
    Next
    INDEX
    Explanations

    phrases related to social interactions and conversations

    oai_token-act-pair · gpt-3.5-turbo
    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
    DragonMagazine
    -0.69
    Reviewer
    -0.68
     exploits
    -0.67
     Parties
    -0.64
     Created
    -0.64
    indal
    -0.62
    î
    -0.62
    hare
    -0.62
    osate
    -0.61
    Authorities
    -0.61
    POSITIVE LOGITS
     chuckle
    1.28
     grin
    1.27
     smile
    1.24
     nodding
    1.23
     frown
    1.22
     nodded
    1.21
     shrug
    1.20
     quir
    1.19
     nods
    1.16
     chuck
    1.15
    Activations Density 0.293%

    No Known Activations