© 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. 0-RES-JB
    11. 645
    Prev
    Next
    INDEX
    Explanations

    references to "friends" in the text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "friend"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cms
    -0.75
    antry
    -0.73
    ahime
    -0.72
    ovi
    -0.67
    scl
    -0.66
     largeDownload
    -0.66
    ibaba
    -0.65
     cylinders
    -0.64
    ets
    -0.63
    urgical
    -0.62
    POSITIVE LOGITS
     friend
    3.56
    friend
    2.57
     friends
    2.39
     Friend
    2.32
     buddy
    2.23
     colleague
    2.06
    Friend
    2.03
    friends
    1.99
     classmate
    1.95
     acquaintance
    1.84
    Activations Density 0.018%

    No Known Activations