INDEX

Explanations

specific names of individuals and references to their roles or titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 Millions

-0.46

муля

-0.46

 millions

-0.45

 dowry

-0.45

wini

-0.43

Consumer

-0.42

 expéri

-0.42

ulte

-0.42

 censo

-0.42

 juta

-0.41

POSITIVE LOGITS

 geopolitical

0.99

 Foreign

0.97

 foreign

0.96

 security

0.94

 diplomacy

0.92

Foreign

0.90

 Diplomacy

0.88

 Security

0.88

geo

0.87

security

0.84

Activations Density 0.194%

specific names of individuals and references to their roles or titles

No Comments

No Known Activations