© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7-RES-JB
    11. 21430
    Prev
    Next
    INDEX
    Explanations

    phrases related to social connections and group interactions

    oai_token-act-pair · gpt-3.5-turbo

    references to social connections and relationships among people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onet
    -0.70
    ãĥķãĤ©
    -0.70
    iculture
    -0.67
    Timeout
    -0.66
     disproportion
    -0.65
     captcha
    -0.65
    lycer
    -0.63
    Scope
    -0.62
    arbon
    -0.62
    Fram
    -0.62
    POSITIVE LOGITS
     acquaintances
    1.23
     coworkers
    1.19
     classmates
    1.04
     relatives
    1.04
     colleagues
    1.01
     strangers
    1.01
     colleague
    0.99
     neighbours
    0.99
     neighbors
    0.98
    friends
    0.96
    Activations Density 0.213%

    No Known Activations