INDEX

Explanations

words and phrases related to causation and consequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

PreferredItem

-0.70

@[+][

-0.68

ñores

-0.68

 nahilalakip

-0.65

 Paglinawan

-0.64

 opgenomen

-0.63

 mourut

-0.62

 extiende

-0.61

 pouvoit

-0.60

 gesloten

-0.60

POSITIVE LOGITS

 caused

0.78

 causing

0.72

caused

0.70

 caus

0.69

causing

0.68

 laten

0.66

 cause

0.64

 make

0.61

 Caused

0.59

 fait

0.59

Activations Density 0.370%

words and phrases related to causation and consequences

No Comments

No Known Activations