INDEX

Explanations

phrases related to political beliefs and actions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Personendaten

-0.67

Дереккөздер

-0.61

таратура

-0.58

Билгалдахарш

-0.58

Personensuche

-0.56

 poveznice

-0.54

LEncoder

-0.51

sizeCache

-0.50

 saites

-0.49

esserung

-0.49

POSITIVE LOGITS

 oneself

0.82

 living

0.81

 yourself

0.75

 utafitiHapana

0.60

 live

0.60

 reading

0.59

living

0.58

 InputDecoration

0.56

Reading

0.56

 Living

0.55

Activations Density 0.424%

phrases related to political beliefs and actions

No Comments

No Known Activations