© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 24126
    Prev
    Next
    INDEX
    Explanations

    instances of emotional feelings or physical sensations

    oai_token-act-pair · gpt-3.5-turbo

    expressions of emotional 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
    ciating
    -0.70
    ades
    -0.70
    ade
    -0.68
    orem
    -0.67
    Market
    -0.67
    occ
    -0.66
    MET
    -0.65
    eria
    -0.64
     Perform
    -0.62
    auri
    -0.62
    POSITIVE LOGITS
     ashamed
    1.21
     sorry
    1.19
     uneasy
    1.18
     guilty
    1.17
     invincible
    1.14
     humiliated
    1.10
     overwhelmed
    1.09
     nause
    1.09
     uncomfortable
    1.08
     compelled
    1.08
    Activations Density 0.049%

    No Known Activations