© 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. 10-RES-JB
    11. 12898
    Prev
    Next
    INDEX
    Explanations

    phrases related to family and friends

    oai_token-act-pair · gpt-3.5-turbo

    references to family and friends in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Turing
    -0.78
    _(
    -0.67
     (âĪĴ
    -0.66
     WRITE
    -0.66
    Ö¼
    -0.65
     Baal
    -0.65
    vasive
    -0.65
     Ragnarok
    -0.64
    ãĥķãĤ¡
    -0.63
     Metatron
    -0.63
    POSITIVE LOGITS
     friends
    1.44
    friends
    1.20
     acquaintances
    1.17
     siblings
    1.17
     caregivers
    1.12
     neighbors
    1.11
     neighbours
    1.08
     kins
    1.08
     relatives
    1.07
     friendships
    1.05
    Activations Density 0.101%

    No Known Activations