INDEX

Explanations

numerical data points and their formatting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 himo

-0.69

WillAppear

-0.66

 CreateTagHelper

-0.58

出版年

-0.58

__',

-0.52

MENAFN

-0.50

ftagPool

-0.49

 puck

-0.49

GraphicsUnit

-0.48

 Himo

-0.47

POSITIVE LOGITS

0.66

antro

0.55

 International

0.53

oneph

0.52

AFS

0.51

omock

0.51

 المعيارى

0.51

Enllaços

0.51

orgh

0.50

 secondly

0.49

Activations Density 0.377%

numerical data points and their formatting

No Comments

No Known Activations