© 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. 21453
    Prev
    Next
    INDEX
    Explanations

    words related to strong emotions or passionate beliefs

    oai_token-act-pair · gpt-3.5-turbo

    terms related to strong emotions or passionate beliefs

    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
     disadvant
    -0.73
     rapist
    -0.65
    hops
    -0.64
     Solitaire
    -0.64
    wana
    -0.64
     detrim
    -0.64
     Savior
    -0.63
     rhy
    -0.63
     Moses
    -0.61
     Shades
    -0.60
    POSITIVE LOGITS
    ently
    1.18
    uously
    1.07
    uous
    1.05
    idity
    1.03
    ously
    0.97
    arious
    0.97
    ament
    0.94
    ouses
    0.94
    iously
    0.94
    ulent
    0.93
    Activations Density 0.077%

    No Known Activations