INDEX

Explanations

different forms of quotation marks used in text

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

quoted text following quotation marks

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.24.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

#+#

-0.66

jspb

-0.58

(&:

-0.57

 виправивши

-0.52

 Савезне

-0.52

posedge

-0.51

mpz

-0.51

 الرياضيه

-0.50

 فريبيس

-0.50

AISSEE

-0.50

POSITIVE LOGITS

 there

0.59

it

0.50

we

0.47

there

0.45

 they

0.44

you

0.44

 astronomers

0.43

 mathematicians

0.42

 oftentimes

0.42

Activations Density 0.065%

different forms of quotation marks used in text

quoted text following quotation marks

No Comments

No Known Activations