INDEX

Explanations

words that express affirmation or agreement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

Sod

-0.62

Stir

-0.58

Zus

-0.57

 blooming

-0.57

 forgiven

-0.56

toBe

-0.56

 meda

-0.56

 shaking

-0.56

Sod

-0.54

 charging

-0.54

POSITIVE LOGITS

 have

0.97

erdings

0.95

verläs

0.94

pfung

0.91

 propOrder

0.88

avía

0.86

NewUrlParser

0.86

did

0.85

 gave

0.84

had

0.83

Activations Density 0.265%

words that express affirmation or agreement

No Comments

No Known Activations