INDEX

Explanations

phrases indicating companionship or collaboration

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 contextLoads

-0.56

 skrift

-0.52

Практи

-0.50

qian

-0.49

 scorpion

-0.49

SCN

-0.48

 Sixt

-0.48

documentclass

-0.48

 rendah

-0.48

ProcessEvent

-0.47

POSITIVE LOGITS

AndEndTag

1.00

 plus

0.89

besides

0.88

 besides

0.87

 ModelExpression

0.86

together

0.81

Alongside

0.81

 Alongside

0.80

 including

0.78

MessageTagHelper

0.78

Activations Density 0.084%

phrases indicating companionship or collaboration

No Comments

No Known Activations