INDEX

Explanations

phrases related to legal terms and agreements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

paces

-0.63

礙

-0.61

ريس

-0.60

Continues

-0.60

amet

-0.59

Segoe

-0.58

 Same

-0.57

no

-0.57

ophor

-0.57

menter

-0.57

POSITIVE LOGITS

RenderAtEndOf

0.98

 themſelves

0.93

ſelf

0.91

 himſelf

0.89

 myſelf

0.84

 betweenstory

0.84

 deſt

0.82

 itſelf

0.81

 Reſ

0.79

 ſhe

0.78

Activations Density 0.246%

phrases related to legal terms and agreements

No Comments

No Known Activations