INDEX

Explanations

instances of the word "using" in various contexts

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

instances of the word "using."

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

describes how something is done

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.20.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

 brancas

-0.55

 geodesic

-0.51

GNP

-0.51

סף

-0.51

 borealis

-0.51

stdafx

-0.51

 Cæsar

-0.50

 чтобы

-0.50

ungguhnya

-0.49

BnF

-0.49

POSITIVE LOGITS

the

0.89

 either

0.85

gyz

0.76

 various

0.76

GEBURTSDATUM

0.73

 both

0.72

 behulp

0.72

ſtra

0.69

 their

0.69

its

0.69

Activations Density 0.080%

instances of the word "using" in various contexts

instances of the word "using."

describes how something is done

No Comments

No Known Activations