INDEX

Explanations

elements and formatting related to mathematical equations or expressions

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 myſelf

-1.01

 himſelf

-0.98

 itſelf

-0.96

Efq

-0.91

ſelves

-0.90

 Reſ

-0.89

 Majefty

-0.88

 themſelves

-0.86

 purpoſe

-0.85

 ſhould

-0.82

POSITIVE LOGITS

ಡಿ

0.53

integrate

0.52

 welcome

0.51

AddTagHelper

0.49

 estimés

0.48

 Mitchell

0.48

 Hansen

0.48

//

0.47

in

0.47

of

0.47

Activations Density 0.667%

elements and formatting related to mathematical equations or expressions

No Known Activations