INDEX

Explanations

references to the current year and related timeframes

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

this year

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

WriteLiteral

-0.50

ueuse

-0.44

retum

-0.43

ilica

-0.43

言えば

-0.41

台の

-0.40

MÁS

-0.40

好みの

-0.40

InstrumentedTest

-0.39

pú

-0.39

POSITIVE LOGITS

ORROW

0.64

today

0.60

TODAY

0.58

Tomorrow

0.57

Tonight

0.57

 today

0.57

Today

0.56

 Tomorrow

0.54

tomorrow

0.54

MemoryWarning

0.54

Activations Density 0.010%

references to the current year and related timeframes

this year

No Comments

No Known Activations