INDEX

Explanations

expressions of agreement or consensus

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

Datuak

-0.72

dal

-0.67

="../

-0.65

hemia

-0.65

://

-0.65

 "..\..\

-0.65

忱

-0.64

*}\

-0.63

 presence

-0.63

ortal

-0.62

POSITIVE LOGITS

 agree

2.92

 Agree

2.84

 agrees

2.81

 agreed

2.63

agree

2.56

 agreeing

2.47

 Agreed

2.47

Agree

2.45

agreed

2.42

 AGRE

2.27

Activations Density 0.078%

expressions of agreement or consensus

No Comments

No Known Activations