INDEX

Explanations

phrases related to leadership statements and public announcements.

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

numerical values or technical information.

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

the beginning of news articles or informational text passages.

oai_token-act-pair · claude-3-5-sonnet-20240620 Triggered by @bot

Code-related tokens or symbols

np_acts-logits-general · gemini-2.0-flash

Hillary Clinton

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

aria

-0.48

нен

-0.47

 Einkauf

-0.46

zo

-0.46

ant

-0.45

tipp

-0.44

ross

-0.43

ons

-0.43

Klas

-0.43

Keep

-0.42

POSITIVE LOGITS

Sqft

1.01

InSection

0.82

\{\\

0.80

 שוליים

0.80

mybatisplus

0.79

setVerticalGroup

0.78

BibitemShut

0.78

principalColumn

0.76

qrstuvwxyz

0.75

 doubtnut

0.75

Activations Density 0.061%

phrases related to leadership statements and public announcements.

numerical values or technical information.

the beginning of news articles or informational text passages.

Code-related tokens or symbols

Hillary Clinton

No Comments

No Known Activations