INDEX

Explanations

commands or instructions related to ensuring correctness and making decisions

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

ябре

-0.70

ItemBackground

-0.68

UnknownFields

-0.64

 дописавши

-0.59

 beginnetje

-0.58

heiser

-0.56

Datuak

-0.54

 puissiez

-0.54

TestingModule

-0.54

 trưởng

-0.53

POSITIVE LOGITS

 sure

2.90

sure

1.99

 SURE

1.86

 Sure

1.72

Sure

1.70

 sûr

1.50

 certain

1.45

 sicher

1.32

certain

1.21

 sûre

1.19

Activations Density 0.216%

commands or instructions related to ensuring correctness and making decisions

No Comments

No Known Activations