INDEX

Explanations

mentions of the letter "J" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_22/width_16k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.hook_mlp_out

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

specialchars

-0.63

modb

-0.63

SequentialGroup

-0.61

withOpacity

-0.60

 correctes

-0.58

Reentrant

-0.58

 LCCN

-0.57

DropTable

-0.54

 onPostExecute

-0.52

 recueil

-0.52

POSITIVE LOGITS

IsMutable

0.57

PostInfinity

0.54

Personendaten

0.54

省市镇

0.53

 linkovi

0.53

withIdentifier

0.51

]").

0.50

 tartalomajánló

0.49

kuuta

0.49

日閲覧

0.49

Activations Density 0.066%

mentions of the letter "J" in various contexts

No Comments

No Known Activations