INDEX

Explanations

segments related to user interaction or navigation prompts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

URLException

-0.82

+#+#

-0.73

 '\\;'

-0.68

✨:

-0.67

IntoConstraints

-0.64

>--}}

-0.63

matchCondition

-0.63

الحياه

-0.62

 initWithFrame

-0.61

 pylint

-0.60

POSITIVE LOGITS

 read

1.60

read

1.57

 Read

1.52

Read

1.48

 READ

1.23

READ

1.19

 reads

1.15

 reading

1.06

Lire

1.06

続きを読む

1.05

Activations Density 0.191%

segments related to user interaction or navigation prompts

No Comments

No Known Activations