INDEX

Explanations

occurrences of the letter 'y' in various forms and contexts

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

words ending in ey

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

存于互联网档案馆

-0.51

ToBounds

-0.48

ocino

-0.48

исленность

-0.47

 Danville

-0.46

니다

-0.46

 thự

-0.46

EDC

-0.45

 oprot

-0.45

fjspx

-0.45

POSITIVE LOGITS

ey

1.22

bey

1.16

vey

1.15

aley

1.09

hey

1.06

cey

1.00

tey

0.98

wey

0.97

dey

0.97

rey

0.96

Activations Density 0.019%

occurrences of the letter 'y' in various forms and contexts

words ending in ey

No Comments

No Known Activations