INDEX

Explanations

the word "working" and its variations, indicating a focus on work-related contexts or processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 defaultstate

-1.03

QMetaType

-0.93

 NSCoder

-0.93

URLException

-0.92

دانشنامهٔ

-0.89

 تضيفلها

-0.86

 GBIF

-0.82

 abstrait

-0.82

 rempliss

-0.81

yym

-0.81

POSITIVE LOGITS

 working

3.00

 Working

2.91

Working

2.86

 WORKING

2.67

working

2.61

WORKING

2.50

 trabajando

1.30

 operating

1.20

 Arbeits

1.18

 functioning

1.13

Activations Density 0.069%

the word "working" and its variations, indicating a focus on work-related contexts or processes

No Comments

No Known Activations