INDEX

Explanations

phrases indicating varying conditions or levels across different samples or contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

yordu

-0.53

Становништво

-0.50

æk

-0.50

 capito

-0.46

他

-0.45

stb

-0.45

навли

-0.45

AddTagHelper

-0.43

ETHING

-0.43

 donc

-0.42

POSITIVE LOGITS

ContentAsync

0.78

WaitGroup

0.73

errHandler

0.71

ServiceModel

0.64

writeFieldEnd

0.58

хьтан

0.58

richTextPanel

0.56

IndentedString

0.56

AccessorTable

0.55

glGen

0.55

Activations Density 0.281%

phrases indicating varying conditions or levels across different samples or contexts

No Comments

No Known Activations