INDEX

Explanations

phrases indicating similarity or sameness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 propia

-0.63

 propio

-0.61

 préfère

-0.60

 préfé

-0.60

льше

-0.60

 surla

-0.58

 apalagi

-0.57

@"/

-0.57

 alguna

-0.57

 meglio

-0.56

POSITIVE LOGITS

 thing

1.37

 exact

1.23

exact

0.98

 Exact

0.98

 EXACT

0.97

thing

0.91

 THING

0.90

 amount

0.87

 coisa

0.79

Exact

0.77

Activations Density 0.200%

phrases indicating similarity or sameness

No Comments

No Known Activations