INDEX

Explanations

indicators of document structure or formatting

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

Appearing before end of turn

np_acts-logits-general · gemini-2.0-flash

sentence or section endings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

LookAnd

-0.60

ftagPool

-0.57

 &___

-0.56

verifyException

-0.56

rungsseite

-0.51

ceğine

-0.50

GTCX

-0.48

osph

-0.46

enterOuterAlt

-0.46

#+#

-0.46

POSITIVE LOGITS

ませんか

0.37

ChildScrollView

0.36

onOptions

0.35

 SEDS

0.35

 jointly

0.35

Pranala

0.35

 виправивши

0.34

 estri

0.34

 مشين

0.33

nellement

0.33

Activations Density 0.134%

indicators of document structure or formatting

Appearing before end of turn

sentence or section endings

No Comments

No Known Activations