INDEX

Explanations

information related to healthcare or medical services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

RenderAtEndOf

-1.05

expandindo

-1.03

 Normdatei

-0.98

+#+#

-0.94

RectangleBorder

-0.94

تقاوى

-0.91

$_"

-0.86

Hochspringen

-0.86

migrationBuilder

-0.85

bootstrapcdn

-0.85

POSITIVE LOGITS

 committed

0.71

 focused

0.65

 dedicated

0.64

 provides

0.64

 strives

0.61

 providing

0.61

 proudly

0.58

私たちは

0.57

 striving

0.57

致力于

0.57

Activations Density 0.224%

information related to healthcare or medical services

No Comments

No Known Activations