INDEX

Explanations

lists or collections of suggestions or resources

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

Numbers followed by nouns

np_acts-logits-general · gemini-2.0-flash

number or quantifier before items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

argout

-0.62

medriver

-0.57

ValueStyle

-0.56

 ComVisible

-0.52

writeFieldEnd

-0.51

хьтан

-0.51

setdefault

-0.50

MigrationBuilder

-0.49

Rohy

-0.48

 NDEBUG

-0.48

POSITIVE LOGITS

 ways

1.53

 reasons

1.40

 things

1.16

 Ways

1.16

reasons

1.09

 WAYS

1.06

Ways

1.06

 Reasons

1.03

 façons

0.99

Reasons

0.97

Activations Density 0.328%

lists or collections of suggestions or resources

Numbers followed by nouns

number or quantifier before items

No Comments

No Known Activations