INDEX

Explanations

phrases associated with causation or effects of actions

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

 Tatsache

-0.83

קישורים

-0.74

 للمعارف

-0.73

 mellitus

-0.72

 strå

-0.71

Ema

-0.69

 Betts

-0.68

SqlClient

-0.68

Adri

-0.67

##

-0.67

POSITIVE LOGITS

 CAUSE

1.54

 cause

1.50

 Cause

1.46

 Causes

1.43

 Caus

1.42

 causes

1.41

causes

1.40

 caused

1.36

cause

1.35

caused

1.34

Activations Density 0.116%

phrases associated with causation or effects of actions

No Comments

No Known Activations