© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 590
    Prev
    Next
    INDEX
    Explanations

    the word "friends."

    oai_token-act-pair · gpt-4-turbo

    mentions of friends in social contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of friends

    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
    hner
    -0.73
    phas
    -0.70
    yss
    -0.69
    arcity
    -0.67
    uchin
    -0.66
    assion
    -0.65
    pmwiki
    -0.63
    ourn
    -0.63
    vent
    -0.62
    grim
    -0.62
    POSITIVE LOGITS
     friends
    1.06
    hips
    1.03
     buddies
    1.00
    Friends
    0.95
     Friends
    0.95
    friends
    0.91
     acquaintances
    0.88
     collaborators
    0.85
    mates
    0.82
     buddy
    0.82
    Activations Density 0.021%

    No Known Activations