INDEX

Explanations

occurrences of job and product-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

RectangleBorder

-0.86

StructEnd

-0.81

Hozzáférés

-0.77

 jScrollPane

-0.75

MLLoader

-0.75

JspWriter

-0.74

 kasarigan

-0.73

DeleteBehavior

-0.73

 سكانية

-0.72

PerformLayout

-0.71

POSITIVE LOGITS

libft

0.52

 select

0.43

Dev

0.41

Car

0.40

 Main

0.40

契

0.39

Cou

0.39

ster

0.39

激

0.39

伏

0.39

Activations Density 0.138%

occurrences of job and product-related terms

No Comments

No Known Activations