INDEX

Explanations

mentions of the word "coverage."

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

SharedDtor

-0.76

 CascadeType

-0.61

wendig

-0.61

HostException

-0.59

:\/\/

-0.57

 Schn

-0.57

PerformLayout

-0.57

@"/

-0.56

esac

-0.56

jsonwebtoken

-0.54

POSITIVE LOGITS

 coverage

3.35

 Coverage

3.19

coverage

3.06

Coverage

2.98

 COVERAGE

2.79

 cobertura

1.73

 copertura

1.23

bertura

1.20

 couverture

1.18

 Covered

1.18

Activations Density 0.125%

mentions of the word "coverage."

No Comments

No Known Activations