INDEX

Explanations

references to "smart" and its variations in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 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

 betweenstory

-1.25

expandindo

-0.91

évaluateur

-0.90

WriteTagHelper

-0.89

 المعيارى

-0.87

 resourceCulture

-0.84

yntaxException

-0.83

 AssemblyTitle

-0.82

 Walkover

-0.80

scriptcase

-0.80

POSITIVE LOGITS

 smart

0.69

 Smart

0.68

smar

0.63

 SMART

0.59

Smart

0.58

 smarter

0.57

 smartly

0.56

est

0.56

smart

0.55

ening

0.54

Activations Density 0.073%

references to "smart" and its variations in various contexts

No Comments

No Known Activations