© 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. 21474
    Prev
    Next
    INDEX
    Explanations

    phrases related to social interaction and community building

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to social interaction and community engagement

    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
    SpaceEngineers
    -0.83
     thrott
    -0.81
     abort
    -0.80
     draconian
    -0.79
     Armageddon
    -0.77
    osate
    -0.74
     looph
    -0.73
     treason
    -0.73
     blackmail
    -0.72
     extortion
    -0.72
    POSITIVE LOGITS
     interact
    1.02
     friendships
    1.00
     perspectives
    1.00
     mentors
    0.99
     interacting
    0.97
     experiences
    0.96
     kindness
    0.95
     volunteering
    0.95
     inspires
    0.95
     collabor
    0.94
    Activations Density 0.495%

    No Known Activations