INDEX

Explanations

the word "par" in various forms and contexts

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

vertx

-0.63

modb

-0.55

 insuffisamment

-0.53

исленность

-0.51

prá

-0.51

теристики

-0.50

labus

-0.49

ッケージ

-0.49

Aws

-0.49

ngthen

-0.47

POSITIVE LOGITS

+#+#

0.71

par

0.65

Par

0.65

PAR

0.61

ChromeDriver

0.61

par

0.60

Par

0.60

 Paral

0.55

 Paro

0.54

 CGRectMake

0.54

Activations Density 0.079%

the word "par" in various forms and contexts

No Comments

No Known Activations