INDEX

Explanations

questions or statements that seek clarification or further understanding

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

事は

-0.59

ことは

-0.50

 ホイール

-0.48

ied

-0.47

 것은

-0.47

while

-0.45

 возможно

-0.45

することは

-0.44

一點

-0.44

 redan

-0.43

POSITIVE LOGITS

новниш

0.77

 cherchés

0.77

 most

0.75

migrationBuilder

0.73

SharedDtor

0.71

 ویکی‌پدیای

0.70

########.

0.68

tanleria

0.67

 healthiest

0.67

 surla

0.65

Activations Density 0.202%

questions or statements that seek clarification or further understanding

No Comments

No Known Activations