INDEX

Explanations

references to observational and experimental study designs

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

preceding clinical trial study types

np_acts-logits-general · gemini-2.0-flash

prospective randomized study

np_acts-logits-general · gemini-2.5-flash-lite

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

__(/*!

-0.49

zarchiwizowane

-0.49

Revenir

-0.47

mering

-0.46

푼

-0.45

\|\

-0.44

rmtree

-0.43

τηση

-0.43

}),

-0.42

 persona

-0.42

POSITIVE LOGITS

 study

1.12

 randomized

1.08

 randomised

1.06

 Study

0.99

 retrospective

0.94

 Randomized

0.94

study

0.92

Study

0.87

 STUDY

0.87

 pilot

0.87

Activations Density 1.179%

references to observational and experimental study designs

preceding clinical trial study types

prospective randomized study

No Comments

No Known Activations