INDEX

Explanations

vocabulary associated with ongoing involvement and connections in various contexts

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

after certain nouns

np_acts-logits-general · gemini-2.0-flash

adjective describing a state or characteristic

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

StoreMessageInfo

-0.49

 propOrder

-0.40

__(/*!

-0.40

Referències

-0.38

Dropped

-0.38

Бележки

-0.37

CrossRef

-0.36

 PARSER

-0.36

hésite

-0.36

 istore

-0.36

POSITIVE LOGITS

 Walkover

0.45

ifikant

0.44

исленность

0.42

servable

0.41

HostException

0.41

izard

0.40

 indirectly

0.39

keyColumn

0.39

Cursed

0.38

atiker

0.38

Activations Density 0.444%

vocabulary associated with ongoing involvement and connections in various contexts

after certain nouns

adjective describing a state or characteristic

No Comments

No Known Activations