INDEX

Explanations

statements expressing knowledge, agreement, and opinion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 tartalomajánló

-1.27

Efq

-1.14

 Majefty

-1.00

 pleaſure

-0.99

 houſe

-0.99

 Houſe

-0.98

 greateſt

-0.97

 himſelf

-0.97

 Theſe

-0.95

 Reſ

-0.94

POSITIVE LOGITS

it

0.60

 sure

0.60

 think

0.55

гим

0.52

 honestly

0.52

the

0.52

 уж

0.51

if

0.49

 tror

0.49

Activations Density 0.241%

statements expressing knowledge, agreement, and opinion

No Comments

No Known Activations