INDEX

Explanations

punctuation marks, specifically periods and commas

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 purpoſe

-1.00

 myſelf

-0.93

 themſelves

-0.92

 reaſon

-0.92

 pleaſure

-0.91

 ſtate

-0.91

 perfons

-0.90

 himſelf

-0.89

 uſed

-0.89

 itſelf

-0.89

POSITIVE LOGITS

...

0.94

…

0.88

...

0.75

…

0.74

....

0.66

……

0.62

......

0.59

“...

0.58

--

0.58

CloseOperation

0.58

Activations Density 0.188%

punctuation marks, specifically periods and commas

No Comments

No Known Activations