INDEX

Explanations

words related to categorization and description of clients and their attributes

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

Geplaatst

-0.83

NOPQRST

-0.82

</thead>

-0.73

 disambiguazione

-0.70

OGND

-0.70

 VizieR

-0.70

webElementGuid

-0.68

 Normdatei

-0.67

новништво

-0.67

новниш

-0.66

POSITIVE LOGITS

 alike

0.77

 Lijst

0.48

둘

0.43

BASELINE

0.43

elle

0.43

 both

0.43

 models

0.42

FieldType

0.41

 всеми

0.41

 dynamic

0.40

Activations Density 0.810%

words related to categorization and description of clients and their attributes

No Comments

No Known Activations