INDEX

Explanations

references to manipulative or deceitful behaviors in relation to political or economic contexts

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

 通販

-0.63

TagMode

-0.63

 tatuagens

-0.61

queryInterface

-0.60

 staden

-0.58

 habet

-0.57

ApiModelProperty

-0.56

 pidana

-0.56

 jambes

-0.55

 nahilalakip

-0.53

POSITIVE LOGITS

RegressionTest

0.69

 bullshit

0.51

ped

0.50

 propaganda

0.49

 obses

0.49

 blink

0.48

BS

0.48

ziz

0.47

ftagPool

0.47

paganda

0.47

Activations Density 0.879%

references to manipulative or deceitful behaviors in relation to political or economic contexts

No Comments

No Known Activations