INDEX

Explanations

phrases indicating possession or ownership

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

migrationBuilder

-1.06

 itſelf

-0.91

Efq

-0.87

GraphicsUnit

-0.86

OrBuilder

-0.86

StoryboardSegue

-0.86

 ſche

-0.86

ſelf

-0.85

 Normdatei

-0.84

Tiene

-0.82

POSITIVE LOGITS

 have

1.23

have

1.04

 make

0.88

 continue

0.86

 appear

0.83

 come

0.78

make

0.77

are

0.73

 seem

0.71

be

0.68

Activations Density 0.322%

phrases indicating possession or ownership

No Comments

No Known Activations