Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 24277
    Prev
    Next
    INDEX
    Explanations

    phrases related to close friendships

    oai_token-act-pair · gpt-3.5-turbo

    references to friendships and close relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arcity
    -0.73
    mington
    -0.70
    aqu
    -0.70
    ounty
    -0.68
    onew
    -0.66
    ulk
    -0.64
    overe
    -0.64
     probabilities
    -0.63
    printed
    -0.63
    Interstitial
    -0.63
    POSITIVE LOGITS
     confid
    0.99
     collaborators
    0.94
     collaborator
    0.94
    lier
    0.92
    hips
    0.89
     buddies
    0.88
     colleagues
    0.86
     colleague
    0.80
    hip
    0.80
     partner
    0.78
    Activations Density 0.084%

    No Known Activations