© 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. 9-RES-JB
    11. 1424
    Prev
    Next
    INDEX
    Explanations

    strong emotional reactions, especially negative ones like shock, disappointment, or anger

    oai_token-act-pair · gpt-3.5-turbo

    emotional expressions of disappointment, frustration, and shock

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imum
    -0.84
    iatures
    -0.73
     Formation
    -0.72
    士
    -0.71
     Pipe
    -0.70
    vre
    -0.69
     Attribution
    -0.68
    utical
    -0.68
    aceutical
    -0.67
     Delivery
    -0.67
    POSITIVE LOGITS
     saddened
    1.55
     dismay
    1.44
     disappointed
    1.34
     anxious
    1.33
     disgusted
    1.32
     ashamed
    1.31
     embarrassed
    1.29
     alarmed
    1.27
     frustrated
    1.27
     appalled
    1.27
    Activations Density 0.326%

    No Known Activations