INDEX

Explanations

references to organizations and their actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 فريبيس

-0.80

batis

-0.64

cillor

-0.64

XtraGrid

-0.62

 BoxFit

-0.60

=\""

-0.60

Diweddarwch

-0.60

躇

-0.59

 pinulongan

-0.59

 تانيه

-0.58

POSITIVE LOGITS

AntiForgeryToken

0.66

Handlung

0.65

룸

0.61

 recently

0.52

<bos>

0.52

0.51

[toxicity=0]

0.51

 sibi

0.50

 broadly

0.50

0.49

Activations Density 0.251%

references to organizations and their actions

No Comments

No Known Activations