INDEX

Explanations

instances of agreement or disagreement in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

Rox

-0.69

Koz

-0.69

Bul

-0.68

Dal

-0.67

="../

-0.65

Mal

-0.65

dal

-0.62

 presence

-0.62

IN

-0.61

</h2>

-0.61

POSITIVE LOGITS

 Agree

1.64

 agrees

1.54

 Disagree

1.50

 Agre

1.48

agree

1.41

 Agreed

1.40

 agree

1.39

 Agreements

1.37

Agree

1.37

 AGRE

1.37

Activations Density 0.101%

instances of agreement or disagreement in the text

No Comments

No Known Activations