INDEX

Explanations

comparative adjectives that indicate levels of quality or performance

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

migrationBuilder

-0.79

consulté

-0.67

 EnglishChoose

-0.64

esModule

-0.64

esía

-0.61

Personensuche

-0.60

HomeAsUpEnabled

-0.60

ẠI

-0.59

AndEndTag

-0.59

 voyons

-0.58

POSITIVE LOGITS

 than

1.76

than

1.26

 THAN

1.19

Than

1.18

 niż

1.13

 Than

1.06

 clearer

1.01

 tighter

1.01

 hơn

1.00

 firmer

1.00

Activations Density 0.809%

comparative adjectives that indicate levels of quality or performance

No Comments

No Known Activations