INDEX

Explanations

legal terminology and procedural phrases

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 NSCoder

-0.55

KURZBESCHREIBUNG

-0.53

UserScript

-0.48

TagMode

-0.47

ArrowToggle

-0.47

Abitanti

-0.45

])));

-0.45

oredCriteria

-0.43

DrawerToggle

-0.43

 HasFactory

-0.43

POSITIVE LOGITS

 henvisninger

0.41

Laugh

0.38

TokenNameLBRACE

0.37

EndProject

0.35

ivil

0.35

 hende

0.34

 juges

0.34

inery

0.34

ffers

0.34

 насељу

0.33

Activations Density 0.067%

legal terminology and procedural phrases

No Comments

No Known Activations