INDEX

Explanations

mathematical expressions and formulas

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

ContentAsync

-0.67

JvmStatic

-0.55

RegressionTest

-0.52

ReusableCell

-0.49

 sense

-0.49

をかけて

-0.45

}}}}

-0.45

اده

-0.44

をかけ

-0.43

Fre

-0.42

POSITIVE LOGITS

 minus

1.40

−

1.17

 Minus

1.10

1.08

 subtracting

1.06

 subtract

1.03

minus

1.02

 trừ

1.02

Minus

0.98

$-$

0.98

Activations Density 1.429%

mathematical expressions and formulas

No Comments

No Known Activations