INDEX

Explanations

instances of the word "work" and its variations in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

paravant

-1.07

quelize

-1.00

 GIPHY

-0.95

zbęd

-0.94

 Enfield

-0.93

 purpoſe

-0.92

CTP

-0.88

 myſelf

-0.88

 Aerosol

-0.87

 desconhe

-0.86

POSITIVE LOGITS

 work

1.78

 Work

1.59

Work

1.59

work

1.56

 WORK

1.54

 works

1.52

WORK

1.45

 Works

1.35

Works

1.31

works

1.29

Activations Density 0.132%

instances of the word "work" and its variations in different contexts

No Comments

No Known Activations