INDEX

Explanations

instances of the word "use" in various contexts

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

use

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ptăm

-0.58

 McNally

-0.57

retudo

-0.53

parsedMessage

-0.53

migrationBuilder

-0.52

Palmar

-0.52

charAt

-0.52

 argint

-0.51

 Kessler

-0.51

 BorderRadius

-0.50

POSITIVE LOGITS

use

1.10

Use

1.06

Use

1.05

use

0.96

USE

0.91

Uses

0.90

 Uses

0.87

 uses

0.86

USE

0.85

 used

0.83

Activations Density 0.202%

instances of the word "use" in various contexts

use

No Comments

No Known Activations