INDEX

Explanations

references to awards and recognition

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

 cool

-0.54

 plus

-0.53

 section

-0.53

plus

-0.52

 незавершена

-0.51

ĩnh

-0.49

can

-0.47

 slick

-0.47

 case

-0.47

的情况下

-0.47

POSITIVE LOGITS

SPATH

0.66

 doInBackground

0.66

TypedDataSet

0.63

XmlAccessType

0.61

 hereto

0.60

Compat

0.59

setVerticalGroup

0.58

 remitted

0.58

ISupport

0.58

szönöm

0.57

Activations Density 0.256%

references to awards and recognition

No Comments

No Known Activations