© 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. 2641
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical well-being and personal feelings

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to personal well-being and health status

    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
     Differences
    -0.73
     intrusion
    -0.70
     Opposition
    -0.67
    allic
    -0.67
     Critics
    -0.67
     Whale
    -0.65
     opposes
    -0.65
     Influence
    -0.64
    cific
    -0.64
     Adds
    -0.64
    POSITIVE LOGITS
     thankful
    1.35
     enjoying
    1.30
     grateful
    1.29
     happier
    1.26
     happiest
    1.20
     exhausted
    1.20
     happy
    1.19
     glad
    1.17
     ready
    1.17
     recovering
    1.16
    Activations Density 0.350%

    No Known Activations