INDEX

Explanations

terms related to images and media elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 configureStore

-0.70

 Trost

-0.62

Gweler

-0.61

mlen

-0.59

://"

-0.56

cline

-0.55

XmlEnum

-0.53

ptid

-0.53

elemField

-0.53

peli

-0.53

POSITIVE LOGITS

images

1.35

 images

1.10

 photos

1.09

Images

1.08

 pictures

1.08

Photos

1.06

 Photos

1.01

 photographs

1.00

 Images

0.98

photos

0.97

Activations Density 0.040%

terms related to images and media elements

No Comments

No Known Activations