INDEX

Explanations

references to various industries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 industry

-0.62

 ammat

-0.57

 SwitchCompat

-0.56

 мѣ

-0.54

jspx

-0.54

 ویکی‌پدی

-0.54

industry

-0.53

Wra

-0.51

Industry

-0.51

 düğ

-0.51

POSITIVE LOGITS

 industries

1.14

 Industries

1.07

 INDUSTRIES

1.02

Industries

0.96

industries

0.87

 sectors

0.83

 Mega

0.73

 Sectors

0.69

\{\\

0.68

Mega

0.65

Activations Density 0.080%

references to various industries

No Comments

No Known Activations