© 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. 11-RES-JB
    11. 9846
    Prev
    Next
    INDEX
    Explanations

    phrases related to strong emotional reactions

    oai_token-act-pair · gpt-3.5-turbo

    negative emotions and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    izons
    -0.83
     successors
    -0.80
    pointer
    -0.73
     2050
    -0.73
     Flavoring
    -0.72
    omial
    -0.71
    alties
    -0.68
    ":"/
    -0.68
     Attributes
    -0.68
    anguages
    -0.67
    POSITIVE LOGITS
     surreal
    1.30
     traumatic
    1.29
     stressful
    1.25
     harrowing
    1.23
     upsetting
    1.21
     traumat
    1.21
     chaotic
    1.20
     heartbreaking
    1.18
     humiliating
    1.18
     shocking
    1.17
    Activations Density 0.256%

    No Known Activations