INDEX

Explanations

keywords related to specific legal and political contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

ValueStyle

-0.87

HideFlags

-0.70

 avoient

-0.69

 HasFactory

-0.69

kuuta

-0.69

 virke

-0.67

 Offisielt

-0.66

 slutet

-0.66

seamnă

-0.66

 étoit

-0.65

POSITIVE LOGITS

to

0.99

0.82

 Gets

0.72

 ready

0.70

 gets

0.69

 turns

0.68

vs

0.67

‘

0.65

 update

0.65

Gets

0.64

Activations Density 0.202%

keywords related to specific legal and political contexts

No Comments

No Known Activations