© 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. 16007
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "with" followed by a combination of other words

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating companionship or association with other 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
    izu
    -0.80
    itution
    -0.79
    urgy
    -0.71
    uncture
    -0.71
    é»Ĵ
    -0.71
    Honestly
    -0.71
    CPU
    -0.70
    anity
    -0.69
    direction
    -0.69
    ongyang
    -0.69
    POSITIVE LOGITS
     fellow
    1.40
     colleagues
    1.32
     colleague
    1.19
     others
    1.13
     friends
    1.11
     associates
    1.07
     collaborators
    1.06
     his
    1.06
     relatives
    1.05
     classmates
    1.03
    Activations Density 0.299%

    No Known Activations