INDEX

Explanations

references to political authority and power dynamics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 Puget

-0.46

Texas

-0.46

 Texas

-0.41

加州

-0.41

 mexic

-0.41

 validamos

-0.41

 Hawaiian

-0.41

 mexicanos

-0.40

 Nantucket

-0.38

 mexicano

-0.38

POSITIVE LOGITS

 reportedly

1.01

 nationalist

0.99

 provincial

0.96

officially

0.88

*++

0.88

 government

0.88

 rumoured

0.88

 unregistered

0.86

 nationalists

0.86

 corruption

0.85

Activations Density 0.845%

references to political authority and power dynamics

No Comments

No Known Activations