INDEX

Explanations

key nouns and verb phrases related to significant actions or events in the context of reporting or analysis

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

body mass index

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

CppMethod

-0.73

 Wikimedijinoj

-0.58

 nakalista

-0.55

InjectAttribute

-0.53

脚注の使い方

-0.49

 nawr

-0.49

المكان

-0.48

Autoritní

-0.47

 Taktlose

-0.47

Tembelea

-0.46

POSITIVE LOGITS

 AssemblyProduct

0.44

 Seeder

0.40

 train

0.37

GEBURTS

0.37

 trains

0.37

Personendaten

0.36

 Roskov

0.36

see

0.36

Gweler

0.35

red

0.35

Activations Density 0.043%

key nouns and verb phrases related to significant actions or events in the context of reporting or analysis

body mass index

No Comments

No Known Activations