INDEX

Explanations

character symbols or punctuation marks related to dialogue or emphasis

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

 صوتيه

-0.77

hoeddwyd

-0.69

StructEnd

-0.58

 MessageBoxIcon

-0.56

raits

-0.56

ffilm

-0.55

|()

-0.54

клопе

-0.54

 Normdatei

-0.53

 Bress

-0.53

POSITIVE LOGITS

´

1.17

0.97

\'

0.84

′

0.83

apos

0.83

 myſelf

0.83

‟

0.78

ʻ

0.76

͛

0.75

ʼ

0.73

Activations Density 0.269%

character symbols or punctuation marks related to dialogue or emphasis

No Comments

No Known Activations