INDEX

Explanations

phrases associated with deception 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 @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

imanapun

-0.70

 vieles

-0.56

TAGS

-0.54

chmal

-0.50

vertret

-0.49

'@/

-0.49

bitField

-0.48

 trovo

-0.47

htë

-0.47

 سياس

-0.47

POSITIVE LOGITS

us

0.90

 everyone

0.84

 readers

0.83

 customers

0.80

 audiences

0.79

 everybody

0.75

you

0.74

 consumers

0.74

everyone

0.73

 people

0.73

Activations Density 0.622%

phrases associated with deception and misinformation

No Comments

No Known Activations