INDEX

Explanations

punctuation marks and their associated contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

”!

-0.76

 již

-0.72

maktadır

-0.64

 Doch

-0.63

Doch

-0.63

 Jednak

-0.62

 Somit

-0.62

-0.60

 sculptured

-0.60

…………………………………………

-0.59

POSITIVE LOGITS

 IIRC

1.11

 iirc

1.11

fucking

1.01

 fucking

0.99

 goddamn

0.99

 fucked

0.99

 shitty

0.98

 FUCKING

0.97

 fuck

0.97

fuck

0.92

Activations Density 0.408%

punctuation marks and their associated contexts

No Comments

No Known Activations