INDEX

Explanations

items that indicate an explanation or list format

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 propOrder

-1.23

Personensuche

-1.07

 nahilalakip

-0.95

Portály

-0.86

 Italijanski

-0.85

featureID

-0.84

-------------</

-0.82

 ویکی‌پدیا

-0.82

SharedDtor

-0.81

таратура

-0.81

POSITIVE LOGITS

0.77

<eos>

0.69

0.68

↵

0.64

0.60

↵↵

0.58

0.56

”

0.55

0.54

Activations Density 0.303%

items that indicate an explanation or list format

No Comments

No Known Activations