INDEX

Explanations

specific identifiers or codes related to various entities or categories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

Bibliograf

-0.49

Ӏ

-0.47

 Barbier

-0.47

 Weid

-0.47

ThemeOverlay

-0.47

urati

-0.45

poved

-0.45

 बै

-0.44

partic

-0.44

 barrera

-0.43

POSITIVE LOGITS

PL

0.96

PLA

0.95

Pla

0.93

Pl

0.91

pla

0.91

 PLAT

0.90

 Plat

0.90

pla

0.89

PL

0.88

pl

0.88

Activations Density 0.233%

specific identifiers or codes related to various entities or categories

No Comments

No Known Activations