INDEX

Explanations

terms related to specific biological conditions or genetic terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

multer

-0.56

Bay

-0.53

utnik

-0.52

 avan

-0.48

bay

-0.47

架

-0.47

appi

-0.46

جات

-0.46

conuts

-0.45

heta

-0.45

POSITIVE LOGITS

SourceChecksum

0.66

 myſelf

0.65

Sé

0.63

 незавершена

0.61

 himſelf

0.61

ſelves

0.61

Sé

0.61

dafx

0.60

 itſelf

0.57

=$?

0.57

Activations Density 0.128%

terms related to specific biological conditions or genetic terminology

No Comments

No Known Activations