INDEX

Explanations

words and phrases related to user input or interaction prompts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 imageName

-0.82

 Whigs

-0.78

oshiba

-0.78

 Meksiku

-0.78

 oldValue

-0.76

 PropTypes

-0.74

akuan

-0.74

 objs

-0.74

uanya

-0.73

PPC

-0.73

POSITIVE LOGITS

 ENTER

1.30

Enter

1.28

 enter

1.25

 entered

1.24

 Enter

1.21

 enters

1.18

enter

1.13

 Entering

1.09

 entering

1.08

ENTER

1.07

Activations Density 0.030%

words and phrases related to user input or interaction prompts

No Comments

No Known Activations