INDEX

Explanations

references to the term "arrow" in various contexts

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

"Arrow", "arrow", or arrow-related terms

np_acts-logits-general · gemini-2.0-flash

arrow, bucket, anchor

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

########.

-0.58

enschappelijke

-0.43

锈钢

-0.43

Diweddarwch

-0.42

 ujednoznacz

-0.41

RTDA

-0.39

PRNewswire

-0.39

談社

-0.39

versiti

-0.39

 latex

-0.38

POSITIVE LOGITS

 miniaturka

0.59

icrous

0.53

WithIOException

0.51

 aapt

0.50

WireFormatLite

0.49

IntoConstraints

0.48

horabuena

0.46

▻

0.46

épar

0.45

⮕

0.44

Activations Density 0.471%

references to the term "arrow" in various contexts

"Arrow", "arrow", or arrow-related terms

arrow, bucket, anchor

No Comments

No Known Activations