INDEX

Explanations

legal terminology and procedural phrases in a legal context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.37.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

 myſelf

-1.05

 pleaſure

-1.04

 ſche

-1.02

 purpoſe

-1.00

 ſte

-0.99

 ſch

-0.99

ſelves

-0.98

 itſelf

-0.98

 Anſ

-0.97

 ſta

-0.97

POSITIVE LOGITS

0.67

«

0.61

■

0.61

}'

0.60

■

0.60

0.58

»

0.57

.'

0.56

/'

0.55

}',

0.54

Activations Density 6.415%

legal terminology and procedural phrases in a legal context

No Comments

No Known Activations