INDEX

Explanations

occurrences of the word "to" 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 @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Mahomet

-0.68

 purpoſe

-0.67

 kaarangay

-0.64

 abel

-0.63

 ſche

-0.59

 Nativity

-0.59

 Sigism

-0.58

 quæ

-0.58

 eiffel

-0.58

 riuscito

-0.57

POSITIVE LOGITS

the

1.03

0.79

hauled

0.70

@",

0.69

UrlResolution

0.69

uate

0.68

enumi

0.67

[toxicity=0]

0.66

OrEqualTo

0.66

"=>"

0.64

Activations Density 0.456%

occurrences of the word "to" in various contexts

No Comments

No Known Activations