INDEX

Explanations

instances of the word "know."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Larsson

-0.59

 Gill

-0.59

huriyet

-0.58

feu

-0.58

 Schiller

-0.57

قای

-0.56

Tig

-0.55

 Efforts

-0.55

گذاری

-0.55

TEntity

-0.55

POSITIVE LOGITS

Know

1.89

 knows

1.88

 Know

1.88

 know

1.86

know

1.85

KNOW

1.81

 Knows

1.79

 KNOW

1.78

knows

1.76

knew

1.72

Activations Density 0.072%

instances of the word "know."

No Comments

No Known Activations