INDEX

Explanations

job-related terms and descriptions, particularly in healthcare and nursing contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.33.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

 OMITBAD

-0.51

 localObject

-0.47

explicit

-0.43

 spørs

-0.43

 Betrachtung

-0.42

发表于

-0.41

 justement

-0.41

 gratuitement

-0.41

 vouloir

-0.40

 hẳn

-0.40

POSITIVE LOGITS

 coordination

0.85

 supervise

0.79

 coordinating

0.75

lia

0.74

 liaison

0.74

 coordinate

0.72

 oversee

0.71

 supervis

0.71

 duties

0.70

 supervision

0.70

Activations Density 0.344%

job-related terms and descriptions, particularly in healthcare and nursing contexts

No Comments

No Known Activations