INDEX

Explanations

terms related to classification and identification in data contexts

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

 mạch

-0.43

زم

-0.40

罩

-0.39

wszy

-0.38

leetcode

-0.36

ורת

-0.36

Bail

-0.36

ムラ

-0.36

 duran

-0.35

 وطن

-0.35

POSITIVE LOGITS

ification

0.93

fied

0.90

ified

0.89

fication

0.87

contentLoaded

0.86

titleMargin

0.84

AutoScaleMode

0.83

ific

0.82

ifications

0.82

IFI

0.80

Activations Density 0.240%

terms related to classification and identification in data contexts

No Comments

No Known Activations