INDEX

Explanations

formatted code or structured data entries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

FormTagHelper

-0.51

 MessageBoxIcon

-0.49

jsii

-0.49

accumulative

-0.48

IFT

-0.48

 crin

-0.48

zewod

-0.47

 swarovski

-0.47

ณ์

-0.47

 Völ

-0.47

POSITIVE LOGITS

 незавершена

0.80

참고

0.65

CompleteListener

0.58

허

0.55

lename

0.55

Referències

0.55

FailureListener

0.55

oucí

0.54

Begriffsklä

0.54

 مكتبه

0.53

Activations Density 0.720%

formatted code or structured data entries

No Comments

No Known Activations