INDEX

Explanations

names of places and characters, particularly in contexts related to narratives or storytelling

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

after capitalized words

np_acts-logits-general · gemini-2.0-flash

place names and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

mudi

-0.49

-0.48

logisch

-0.44

воде

-0.44

URATION

-0.42

と呼ばれる

-0.42

ToolStrip

-0.42

uertos

-0.41

始まり

-0.39

POSITIVE LOGITS

+#+#

1.13

migrationBuilder

0.98

 tartalomajánló

0.87

writeFieldEnd

0.87

OrNil

0.85

 noqa

0.81

 AssemblyVersion

0.80

RTEE

0.78

.")

0.76

.*/

0.74

Activations Density 1.074%

names of places and characters, particularly in contexts related to narratives or storytelling

after capitalized words

place names and organizations

No Comments

No Known Activations