INDEX

Explanations

phrases indicating uncertainty or conditions related to query responses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 noastră

-0.62

 geheel

-0.59

 příslu

-0.55

 pungkasnya

-0.54

</i>

-0.54

 loosely

-0.54

 afstand

-0.54

 voordeel

-0.53

 personales

-0.52

 nevoie

-0.52

POSITIVE LOGITS

uxxxx

0.91

 resourceCulture

0.79

<bos>

0.74

 CreateTagHelper

0.70

AndEndTag

0.70

bkz

0.64

ChildScrollView

0.63

writerow

0.62

 "..\..\

0.61

 &___

0.60

Activations Density 0.349%

phrases indicating uncertainty or conditions related to query responses

No Comments

No Known Activations