© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1-RES-JB
    11. 10450
    Prev
    Next
    INDEX
    Explanations

    expressions or comments emphasizing the intensity of a feeling or action

    oai_token-act-pair · gpt-3.5-turbo

    intense emphasis or affirmations of feelings or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    heid
    -0.77
    enary
    -0.71
    utions
    -0.65
    heny
    -0.63
    oire
    -0.63
     Watch
    -0.61
    ean
    -0.60
     Protection
    -0.60
    iture
    -0.59
     pige
    -0.59
    POSITIVE LOGITS
     bothered
    0.90
     REALLY
    0.89
     darn
    0.84
     bother
    0.83
     bothering
    0.81
     differentiated
    0.76
     really
    0.74
    olkien
    0.74
     pissed
    0.72
     needed
    0.71
    Activations Density 0.036%

    No Known Activations