INDEX

Explanations

terms related to justification or justification concepts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 teken

-0.51

 Señora

-0.49

ренко

-0.48

 sür

-0.48

es

-0.48

umen

-0.48

kmal

-0.47

 Lott

-0.47

pageX

-0.46

VersionUID

-0.46

POSITIVE LOGITS

 Affiliate

0.91

 justify

0.87

 ethical

0.86

richTextPanel

0.85

Mor

0.83

Mor

0.83

 Justification

0.82

 Ethical

0.81

 ethics

0.81

 Italijanski

0.80

Activations Density 0.083%

terms related to justification or justification concepts

No Comments

No Known Activations