INDEX

Explanations

phrases indicating uncertainty or conditionality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.13.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

CLUDING

-0.63

AccessorTable

-0.59

)}^{

-0.59

ECAUSE

-0.57

YourGuide

-0.56

YOUR

-0.56

acy

-0.55

|}{$

-0.55

endregion

-0.54

Slf

-0.53

POSITIVE LOGITS

0.65

 financeira

0.61

 noastre

0.57

 '\\;'

0.55

 heresy

0.54

 frumos

0.54

 nostru

0.53

 AssemblyCompany

0.53

 мәкал

0.53

AndEndTag

0.52

Activations Density 0.018%

phrases indicating uncertainty or conditionality

No Comments

No Known Activations