INDEX

Explanations

references to geographical locations and company affiliations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 collected

-0.30

 Collected

-0.28

 entschieden

-0.26

lüğ

-0.26

 dorada

-0.25

 perfect

-0.24

>>()

-0.24

UserDto

-0.24

 ASSOCIATED

-0.24

POSITIVE LOGITS

 MainAxisSize

0.85

 ivelany

0.78

 '\\;'

0.74

 JpaRepository

0.67

 betweenstory

0.64

elemField

0.63

 AssemblyTitle

0.63

AddTagHelper

0.63

omalainen

0.62

 headquartered

0.61

Activations Density 0.460%

references to geographical locations and company affiliations

No Comments

No Known Activations