INDEX

Explanations

occurrences of the pronoun "we" and related future tense constructions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 scattata

-0.56

 Stands

-0.53

 stirs

-0.51

 springing

-0.50

 tenders

-0.50

 taps

-0.50

 Belt

-0.49

 wartawan

-0.48

న్న

-0.48

stalt

-0.48

POSITIVE LOGITS

 المعيارى

0.76

 unknownFields

0.66

webElementXpaths

0.65

AndroidJUnit

0.64

StructEnd

0.63

 MainAxisSize

0.62

 AssemblyVersion

0.61

 חיצוניים

0.61

DeleteBehavior

0.60

CloseOperation

0.59

Activations Density 0.583%

occurrences of the pronoun "we" and related future tense constructions

No Comments

No Known Activations