INDEX

Explanations

phrases and terms related to measurements and statistical values

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

ugar

-0.49

ง

-0.47

 Pear

-0.46

avor

-0.46

kiri

-0.45

IsPostBack

-0.45

dbo

-0.45

 Materials

-0.45

desen

-0.45

AutoScaleMode

-0.45

POSITIVE LOGITS

ImageContext

0.68

astify

0.65

GIVEREF

0.64

principalColumn

0.62

zzleHttp

0.61

むしろ

0.61

PageModule

0.60

 Pristupljeno

0.60

ModelSerializer

0.60

 sebaliknya

0.59

Activations Density 0.582%

phrases and terms related to measurements and statistical values

No Comments

No Known Activations