INDEX

Explanations

phrases indicating rumors or speculation about individuals and their circumstances

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

TacToe

-0.57

 leçon

-0.55

Diweddarwch

-0.54

 spéciales

-0.53

réhen

-0.50

lenir

-0.49

 lección

-0.49

brei

-0.47

 richtigen

-0.47

oblast

-0.47

POSITIVE LOGITS

 rumour

1.21

 rumor

1.13

 rumours

1.13

 rumoured

1.10

 rumors

1.10

 rumored

1.09

 Rumors

0.96

 leaked

0.89

 speculated

0.87

 reportedly

0.87

Activations Density 0.233%

phrases indicating rumors or speculation about individuals and their circumstances

No Comments

No Known Activations