INDEX

Explanations

the word "by" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 étrangères

-0.48

 بندی

-0.47

GraphicsUnit

-0.46

ize

-0.45

 informée

-0.43

getvalue

-0.42

istic

-0.42

untung

-0.42

AtIndexPath

-0.41

 ovlád

-0.41

POSITIVE LOGITS

 means

1.71

 virtue

1.49

means

1.41

way

1.38

 MEANS

1.28

standers

1.22

Means

1.17

stander

1.15

 dint

1.15

 Means

1.14

Activations Density 0.390%

the word "by" in various contexts

No Comments

No Known Activations