INDEX

Explanations

phrases related to relationships and connections between entities

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

"pair" or "pairs"

np_acts-logits-general · gemini-2.0-flash

key/value pairs

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

 VizieR

-0.50

 handleMessage

-0.43

vânt

-0.42

glises

-0.42

IsContent

-0.41

rscheinlichkeit

-0.41

zież

-0.40

 trưng

-0.40

 ModelExpression

-0.39

glise

-0.39

POSITIVE LOGITS

 pair

2.98

 pairs

2.65

duo

2.53

 Pair

2.52

pair

2.50

 Pairs

2.39

Pair

2.36

 PAIR

2.25

 couple

2.20

pairs

2.18

Activations Density 0.608%

phrases related to relationships and connections between entities

"pair" or "pairs"

key/value pairs

No Comments

No Known Activations