© 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. 1376
    Prev
    Next
    INDEX
    Explanations

    phrases related to intense emotions or expressions of deep regret

    oai_token-act-pair · gpt-3.5-turbo

    expressions of concern and sadness

    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
     Sneak
    -0.83
     swoop
    -0.71
    ounters
    -0.71
     Hedge
    -0.70
     woo
    -0.66
    rosso
    -0.66
     sweeps
    -0.66
     curves
    -0.65
    ivari
    -0.65
     Dancing
    -0.65
    POSITIVE LOGITS
     responsibility
    1.21
     commend
    1.09
     obligation
    1.07
     gratitude
    1.03
     testament
    1.00
     regret
    0.97
     honour
    0.96
     condolences
    0.95
     remorse
    0.94
     disgrace
    0.94
    Activations Density 0.410%

    No Known Activations