INDEX

Explanations

comments and documentation related to software licensing and conditions

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

Code diff headers

np_acts-logits-general · gemini-2.0-flash

code diff hunks

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

addPreferredGap

-0.62

 bellows

-0.55

pulumi

-0.49

adin

-0.48

 représ

-0.46

下一页

-0.46

elemField

-0.44

 Precis

-0.41

complexType

-0.40

 Governor

-0.40

POSITIVE LOGITS

+#+

2.00

#+#

1.94

+#+#

1.46

########.

1.31

:+:

1.20

+:+

1.16

 esternos

0.73

uxxxx

0.72

MessageTagHelper

0.70

Havolalar

0.68

Activations Density 0.028%

comments and documentation related to software licensing and conditions

Code diff headers

code diff hunks

No Comments

No Known Activations