INDEX

Explanations

image-related elements and attributes in the document

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

img html tags

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

SBATCH

-0.66

ỏa

-0.60

ſelves

-0.59

 विश्वसनीयता

-0.59

wpi

-0.58

onien

-0.58

 plaît

-0.57

RTHOOK

-0.57

few

-0.56

</tfoot>

-0.56

POSITIVE LOGITS

img

1.13

img

1.06

Img

1.02

Img

0.91

IMG

0.83

IMG

0.79

 imgs

0.77

imgUrl

0.76

imgs

0.73

Imgs

0.68

Activations Density 0.004%

image-related elements and attributes in the document

img html tags

No Comments

No Known Activations