INDEX

Explanations

references to legal roles and responsibilities, particularly in corporate contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

تقاوى

-0.88

 beginnetje

-0.76

parsedMessage

-0.74

Tikang

-0.73

GEBURTSDATUM

-0.72

 kaarangay

-0.65

 ddelweddau

-0.65

حوالہ

-0.63

 kysy

-0.60

 <=",

-0.60

POSITIVE LOGITS

volley

0.66

 billions

0.60

っこう

0.58

 capital

0.55

 bilhões

0.53

def

0.52

piram

0.50

pedo

0.47

 manifestly

0.47

 global

0.47

Activations Density 0.687%

references to legal roles and responsibilities, particularly in corporate contexts

No Comments

No Known Activations