INDEX

Explanations

exclamation marks and unexpected formatting in the text

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

为例

-0.52

yntaxException

-0.50

avl

-0.48

DateTimeField

-0.47

πάρχ

-0.46

 réessayer

-0.46

assertRaises

-0.46

יוחד

-0.46

 Enfin

-0.45

KommentareTeilen

-0.45

POSITIVE LOGITS

TagMode

0.90



0.80

 Audiodateien

0.68

buttonShape

0.64

↵↵↵↵↵

0.63

gestone

0.62

↵↵↵↵↵↵↵↵↵↵↵↵↵↵

0.60

↵↵↵↵

0.60

</table>

0.59

-------

0.58

Activations Density 0.440%

exclamation marks and unexpected formatting in the text

No Comments

No Known Activations