INDEX

Explanations

the presence of the word "Ar."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

ագրություններ

-0.98

SOUNDBITE

-0.94

 myſelf

-0.86

 Theſe

-0.84

 pleaſure

-0.82

 Anſ

-0.81

webElementXpaths

-0.80

 Beſ

-0.80

 ་་

-0.80

 Diſ

-0.80

POSITIVE LOGITS

Ar

3.09

Ar

2.90

ar

2.56

AR

2.05

 Ар

1.92

ar

1.75

Ар

1.71

AR

1.59

 ар

1.57

Arb

1.35

Activations Density 0.068%

the presence of the word "Ar."

No Comments

No Known Activations