© 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. 7926
    Prev
    Next
    INDEX
    Explanations

    pronouns and possessive adjectives related to health and personal well-being

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize possession and the impact of external factors on individuals and communities

    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
    opus
    -0.76
    aye
    -0.72
    oldemort
    -0.70
    arthed
    -0.70
    hots
    -0.70
     Unsure
    -0.69
    wic
    -0.68
    otom
    -0.68
    dullah
    -0.68
    oned
    -0.67
    POSITIVE LOGITS
     livelihood
    1.56
     credibility
    1.50
     ability
    1.44
     sanity
    1.43
     reputation
    1.36
     chances
    1.29
     integrity
    1.27
     wellbeing
    1.27
     competitiveness
    1.26
     psyche
    1.25
    Activations Density 0.181%

    No Known Activations