INDEX

Explanations

names of people, specifically focusing on 'Jimmy', 'Billy', and 'Williams'

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

 تضيفلها

-0.68

AnchorTagHelper

-0.67

Nad

-0.66

hew

-0.62

Nad

-0.62

dew

-0.57

 Tade

-0.56

Badge

-0.56

CWE

-0.56

 Jayne

-0.56

POSITIVE LOGITS

 Jimmy

1.17

 Williams

1.12

Jimmy

1.05

Williams

1.00

 Tommy

0.97

 Billy

0.96

Billy

0.94

artic

0.93

Tommy

0.93

 Jimmie

0.91

Activations Density 0.083%

names of people, specifically focusing on 'Jimmy', 'Billy', and 'Williams'

No Comments

No Known Activations