INDEX

Explanations

phrases related to legal processes and terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 pleaſure

-0.94

 nakalista

-0.90

 greateſt

-0.88

 purpoſe

-0.87

 beſt

-0.84

 Monfieur

-0.83

 betweenstory

-0.83

 Houſe

-0.83

 Chriftian

-0.83

 myſelf

-0.82

POSITIVE LOGITS

 perhaps

0.57

SizeMode

0.53

 autorytatywna

0.51

 presumably

0.48

 possibly

0.47

protoimpl

0.47

 hopefully

0.46

AdapterView

0.46

 Vogel

0.46

par

0.46

Activations Density 1.214%

phrases related to legal processes and terminology

No Comments

No Known Activations