© 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. 2-RES-JB
    11. 12907
    Prev
    Next
    INDEX
    Explanations

    phrases related to causality or consequence

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate significant emphasis or importance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     scatter
    -0.74
     scattering
    -0.72
     paternal
    -0.66
     stagger
    -0.64
     dirt
    -0.64
     prol
    -0.64
     eleph
    -0.64
     Annotations
    -0.64
     tremend
    -0.63
     cyan
    -0.63
    POSITIVE LOGITS
    ¹
    1.03
    £
    0.96
    º
    0.94
    ¢
    0.89
    ¡
    0.87
    Ī
    0.86
    ¬
    0.85
    į
    0.85
    ı
    0.84
    ¼
    0.84
    Activations Density 0.762%

    No Known Activations