INDEX

Explanations

references to authorship or attribution in texts

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

 pleaſure

-0.73

IsContent

-0.68

 myſelf

-0.61

 whoſe

-0.61

 purpoſe

-0.60

 itſelf

-0.60

 ſche

-0.59

 doméstica

-0.57

XmlAccessType

-0.57

 houſe

-0.56

POSITIVE LOGITS

by

0.87

by

0.86

 oleh

0.73

 kasarigan

0.72

 geslacht

0.68

By

0.65

By

0.65

izr

0.62

 بواسطة

0.60

BY

0.59

Activations Density 0.171%

references to authorship or attribution in texts

No Comments

No Known Activations