INDEX

Explanations

connections between various elements in legal, healthcare, and technology contexts

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

social, legal, and specific nouns

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

aarrggbb

-0.43

 nahilalakip

-0.42

SupportActionBar

-0.40

 استنادى

-0.40

 onOptions

-0.40

phong

-0.39

ServletContext

-0.38

MessageTagHelper

-0.38

readystatechange

-0.37

Equilibrium

-0.37

POSITIVE LOGITS

 دیکھیے

0.57

ſelf

0.48

MessageOf

0.48

ípio

0.48

+#+#

0.47

rungsseite

0.45

 EconPapers

0.45

 fhew

0.44

'',

0.43

ſelves

0.42

Activations Density 0.335%

connections between various elements in legal, healthcare, and technology contexts

social, legal, and specific nouns

No Comments

No Known Activations