INDEX

Explanations

references to fake news and misinformation

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

 primaire

-0.69

 debout

-0.66

ükü

-0.64

CDCl

-0.62

 tarifa

-0.61

 canzoni

-0.59

tamment

-0.58

তথ্যসূত্র

-0.58

modb

-0.58

raszamy

-0.58

POSITIVE LOGITS

 fake

1.29

 Fake

1.24

Fake

1.14

fake

1.11

 Faux

1.03

Faux

1.00

 false

1.00

 faux

0.96

 False

0.93

 pretend

0.93

Activations Density 0.353%

references to fake news and misinformation

No Comments

No Known Activations