INDEX

Explanations

instances of the word "a" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 élevées

-0.57

WebElementEntity

-0.55

больше

-0.54

MLLoader

-0.51

Demografie

-0.50

Plenty

-0.49

 iprot

-0.46

 spricht

-0.45

 собою

-0.44

zelfde

-0.43

POSITIVE LOGITS

 result

1.67

result

1.27

 consequence

1.18

 resultado

1.11

 RESULT

1.07

 Result

1.06

 resultat

1.05

 Ergebnis

1.01

 matter

1.01

Result

1.00

Activations Density 0.126%

instances of the word "a" in various contexts

No Comments

No Known Activations