INDEX

Explanations

connective words and conjunctions that indicate relationships between ideas or phrases

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

appearing before "and" or "or"

np_acts-logits-general · gemini-2.0-flash

and conjunctions

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

 raiſ

-0.55

IndentedString

-0.50

 amarillas

-0.50

 StatefulWidget

-0.47

 artesanales

-0.47

 senhora

-0.46

出版年

-0.45

 NSCoder

-0.45

quinho

-0.45

 vocês

-0.44

POSITIVE LOGITS

SequentialGroup

0.43

luk

0.41

 Rings

0.40

 Ring

0.39

tle

0.39

észetes

0.38

Erl

0.38

 rings

0.38

 Pretty

0.38

 Fair

0.37

Activations Density 0.443%

connective words and conjunctions that indicate relationships between ideas or phrases

appearing before "and" or "or"

and conjunctions

No Comments

No Known Activations