INDEX

Explanations

phrases pertaining to helping, assisting, or supporting others

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

'{@

-0.73

 للمعارف

-0.67

mybatisplus

-0.61

PhysRevLett

-0.58

 jScrollPane

-0.56

Autoritní

-0.56

 kaynağından

-0.55

 cherchés

-0.54

出版年

-0.53

 transfieras

-0.53

POSITIVE LOGITS

 transition

0.73

 navigate

0.69

 navigating

0.69

 справи

0.65

navig

0.59

 разобра

0.59

 finding

0.58

évaluateur

0.58

 cope

0.57

忙

0.56

Activations Density 0.195%

phrases pertaining to helping, assisting, or supporting others

No Comments

No Known Activations