INDEX

Explanations

job-related terminology within healthcare and technology contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 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

 kasarigan

-0.60

ftagPool

-0.59

WriteTagHelper

-0.53

 typelib

-0.52

 HttpNotFound

-0.47

 useAppContext

-0.47

StructEnd

-0.45

 propOrder

-0.45

msgTypes

-0.45

----</

-0.45

POSITIVE LOGITS

uliert

0.46

SourceChecksum

0.45

getJSONObject

0.44

出版年

0.42

 noted

0.42

 marins

0.41

 signature

0.41

 recognised

0.41

 organised

0.41

 purpose

0.41

Activations Density 0.349%

job-related terminology within healthcare and technology contexts

No Comments

No Known Activations