INDEX

Explanations

questions involving the letter "Q" or references to queries

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

neſs

-0.79

 ―――――

-0.78

leſs

-0.76

ſhip

-0.74

 myſelf

-0.70

 ……………………

-0.70

wiſe

-0.69

 itſelf

-0.69

 ――――――――

-0.69

………………………………

-0.68

POSITIVE LOGITS

2.30

2.13

1.70

1.52

ｑ

1.19

Qs

1.16

Ｑ

1.14

iQ

1.02

 Qantas

0.99

qtype

0.99

Activations Density 0.116%

questions involving the letter "Q" or references to queries

No Comments

No Known Activations