INDEX

Explanations

references to the word "zoom" in various contexts

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

zoom in or zoom on

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

<b>

-0.47

}{

-0.40

DataContract

-0.37

<strong>

-0.36

 Keyes

-0.35

り

-0.34

DTD

-0.33

entlicher

-0.33

</b>

-0.32

POSITIVE LOGITS

 Zoom

1.32

 zoom

1.29

Zoom

1.24

 ZOOM

1.22

zoom

1.20

ZOOM

1.11

 zooming

0.93

 zoomed

0.91

ſelf

0.78

ſelves

0.76

Activations Density 0.003%

references to the word "zoom" in various contexts

zoom in or zoom on

No Comments

No Known Activations