INDEX

Explanations

terms that signal transparency or honesty in advertising and service

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

AsStream

-0.72

AndEndTag

-0.63

AutoField

-0.57

BeginInit

-0.54

出版年

-0.53

MMdd

-0.47

detectChanges

-0.47

 CHAPITRE

-0.47

kosti

-0.46

المصدر

-0.46

POSITIVE LOGITS

 unlike

0.81

unlike

0.74

 realistic

0.70

 genuinely

0.64

 honest

0.63

новништво

0.63

 Unlike

0.61

 fair

0.56

 Realistic

0.56

 real

0.55

Activations Density 0.213%

terms that signal transparency or honesty in advertising and service

No Comments

No Known Activations