INDEX

Explanations

phrases that indicate reasoning or justification

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_6/width_16k/average_l0_133

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 %@",

-0.57

makeText

-0.55

 bezeichneter

-0.51

раздо

-0.51

rungsseite

-0.49

getDeclared

-0.49

期刊论文

-0.46

+%

-0.45

apimachinery

-0.45

ệp

-0.45

POSITIVE LOGITS

bootstrapcdn

0.67

 CURIAM

0.63

mergeFrom

0.59

ConstraintMaker

0.59

 AssemblyCulture

0.59

 Statt

0.56

 فريبيس

0.56

показания

0.55

 Zeug

0.55

يار

0.54

Activations Density 0.265%

phrases that indicate reasoning or justification

No Comments

No Known Activations