© 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. 2-RES-JB
    11. 4442
    Prev
    Next
    INDEX
    Explanations

    phrases related to interactions between individuals or groups

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "interaction" and its related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zn
    -0.86
    prus
    -0.83
    aft
    -0.82
    cott
    -0.81
    cise
    -0.77
    haps
    -0.75
    enic
    -0.74
    ussy
    -0.74
    skip
    -0.72
    amina
    -0.71
    POSITIVE LOGITS
     interactions
    1.22
     interaction
    1.11
     interacts
    0.83
    iquette
    0.82
    ivity
    0.81
     interacted
    0.79
    uality
    0.77
     interacting
    0.73
    ively
    0.72
     interact
    0.71
    Activations Density 0.010%

    No Known Activations