INDEX

Explanations

terms related to causation and responsibility

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 سكانية

-0.76

 nakalista

-0.65

 Wiktionnaire

-0.63

 CommonModule

-0.60

Diwedd

-0.55

 nonatomic

-0.55

 currently

-0.54

الإنجليزية

-0.53

MigrationBuilder

-0.53

 horri

-0.53

POSITIVE LOGITS

 Cause

1.17

Cause

1.16

 cause

1.16

cause

1.06

 CAUSE

1.05

CAUSE

0.98

Ty

0.91

Cuz

0.79

cuz

0.77

že

0.74

Activations Density 0.055%

terms related to causation and responsibility

No Comments

No Known Activations