INDEX

Explanations

terms related to measurement and positioning

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

time slot

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

writeFieldEnd

-0.56

 CURIAM

-0.54

MLLoader

-0.50

 Moscú

-0.50

ніципалі

-0.48

CodeAttribute

-0.47

 ویکی‌پدی

-0.47

 acabados

-0.45

 AssemblyCompany

-0.44

ंदीखरीदारी

-0.44

POSITIVE LOGITS

:✨

0.51

 كومونز

0.42

addContainerGap

0.42

 uncin

0.38

astify

0.38

󠁮

0.38

thead

0.37

+#+#

0.35

pea

0.35

noscript

0.35

Activations Density 0.070%

terms related to measurement and positioning

time slot

No Comments

No Known Activations