INDEX

Explanations

words and phrases related to understanding, evaluation, and processes in various contexts, particularly in education and biological systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 Arka

-0.65

 Herod

-0.65

interopRequire

-0.63

)");

-0.62

 alphabetically

-0.62

 BoxDecoration

-0.60

 equator

-0.58

Carriera

-0.58

 LoginForm

-0.57

 Mahomet

-0.57

POSITIVE LOGITS

RegressionTest

0.49

AndEndTag

0.48

 виправивши

0.45

 rate

0.44

slidesToShow

0.44

 cerdo

0.44

tifully

0.42

 насељу

0.42

OUND

0.42

httphttps

0.42

Activations Density 0.751%

words and phrases related to understanding, evaluation, and processes in various contexts, particularly in education and biological systems

No Comments

No Known Activations