INDEX

Explanations

relationships and connections involving the word "with."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

RenderAtEndOf

-0.84

 Mahomet

-0.79

KommentareTeilen

-0.76

 للاسماء

-0.75

 thither

-0.75

 Monfieur

-0.73

 cherchés

-0.72

 فريبيس

-0.72

 poveznice

-0.71

StructEnd

-0.70

POSITIVE LOGITS

 róż

0.58

 بص

0.56

tvguidetime

0.54

 با

0.52

à

0.52

 with

0.52

 having

0.51

holding

0.51

 dengan

0.49

具

0.49

Activations Density 0.266%

relationships and connections involving the word "with."

No Comments

No Known Activations