INDEX

Explanations

legal terms and their associated contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 مرئيه

-0.82

 Normdatei

-0.80

RenderAtEndOf

-0.67

WebVitals

-0.66

 الحره

-0.66

 esetén

-0.63

 déput

-0.63

@[+][

-0.63

DockStyle

-0.62

such

-0.62

POSITIVE LOGITS

+#+#

0.69

曖昧さ回避

0.58

 Catawiki

0.55

felf

0.53

intellij

0.52

 pattern

0.51

 journey

0.49

hoodie

0.47

 MatDialog

0.47

ActionCreators

0.45

Activations Density 1.247%

legal terms and their associated contexts

No Comments

No Known Activations

legal terms and their associated contexts

No Comments

No Known Activations