INDEX

Explanations

references to pictures and photographs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 schrijven

-0.60

<tfoot>

-0.59

WebVitals

-0.59

wrote

-0.56

 createState

-0.54

écrire

-0.51

 CreateTagHelper

-0.49

λογία

-0.48

brainly

-0.48

 wrote

-0.48

POSITIVE LOGITS

 taken

1.12

 depicting

1.05

 showing

1.04

taken

0.86

 illustrating

0.83

 featuring

0.82

 captioned

0.80

showing

0.80

 showcasing

0.78

 depict

0.78

Activations Density 0.387%

references to pictures and photographs

No Comments

No Known Activations