INDEX

Explanations

terms related to academic research and publications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 plus

-0.55

-0.54

-0.51

อก

-0.46

-0.44

затор

-0.43

-0.42

-0.41

grad

-0.41

('

-0.40

POSITIVE LOGITS

 kasarigan

1.08

 تضيفلها

0.99

LookAnd

0.94

UnusedPrivate

0.93

ArrowToggle

0.92

WithIOException

0.92

GEBURTSDATUM

0.91

BibitemShut

0.78

parsedMessage

0.78

AnchorTagHelper

0.78

Activations Density 0.325%

terms related to academic research and publications

No Comments

No Known Activations