INDEX

Explanations

phrases containing important qualifiers and structural components of scientific arguments

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

Not in Any Lists

No Comments

Negative Logits

__*/

-0.72

клопе

-0.58

исленность

-0.56

 незавершена

-0.56

oporosis

-0.56

Portale

-0.55

 discorso

-0.54

 reivindic

-0.53

曖昧さ回避

-0.53

 thiệu

-0.52

POSITIVE LOGITS

 intStringLen

0.66

+#+#

0.62

WebServlet

0.59

posedge

0.58

complexContent

0.56

acty

0.53

inheritDoc

0.53

новниш

0.52

enegro

0.52

findpost

0.51

Activations Density 2.533%

phrases containing important qualifiers and structural components of scientific arguments

No Comments

No Known Activations