INDEX

Explanations

mathematical and scientific terminology related to measurements and calculations

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

/-/

-0.65

“

-0.57

mappedBy

-0.56

jock

-0.52

-0.49

her

-0.48

boy

-0.48

mers

-0.47

/=

-0.46

vay

-0.45

POSITIVE LOGITS

Efq

0.91

 Monfieur

0.90

 himſelf

0.88

 itſelf

0.88

 myſelf

0.87

 ſtate

0.87

 themſelves

0.86

 theſe

0.81

 purpoſe

0.80

 ſta

0.80

Activations Density 0.931%

mathematical and scientific terminology related to measurements and calculations

No Comments

No Known Activations