INDEX

Explanations

the letter "A" and its variations in different cases

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

 Koop

-0.74

 myſelf

-0.70

 Palmeiras

-0.70

 Paradis

-0.70

 Piso

-0.68

 daewoo

-0.68

 Demp

-0.67

 Román

-0.67

bootstrapcdn

-0.67

 morphe

-0.66

POSITIVE LOGITS

а

0.93

omiast

0.82

rungsseite

0.82

And

0.81

But

0.78

argout

0.77

А

0.74

but

0.73

parsedMessage

0.68

onViewCreated

0.67

Activations Density 0.021%

the letter "A" and its variations in different cases

No Comments

No Known Activations