INDEX

Explanations

the word "does" 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 @ 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

 myſelf

-1.85

 itſelf

-1.79

Efq

-1.77

 Monfieur

-1.71

 purpoſe

-1.68

 ſche

-1.64

 Jefus

-1.63

 Theſe

-1.60

 poffible

-1.57

 houſe

-1.56

POSITIVE LOGITS

do

1.92

Do

1.89

 does

1.67

Do

1.55

did

1.53

 Does

1.49

Did

1.45

DO

1.41

Does

1.34

do

1.28

Activations Density 0.237%

the word "does" and its variations in different contexts

No Comments

No Known Activations