INDEX

Explanations

terms associated with specific industries, medical conditions, or categories of items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

Хьажоргаш

-0.46

StoryboardSegue

-0.45

InputBorder

-0.43

 незавершена

-0.41

msgTypes

-0.40

 saites

-0.40

RTSN

-0.38

 AssemblyTitle

-0.38

 wipe

-0.36

 Meinung

-0.35

POSITIVE LOGITS

хьтан

0.66

0.56

 ſtate

0.51

 pleaſure

0.51

 myſelf

0.49

 nahilalakip

0.49

 diſt

0.48

 houſe

0.47

ſhip

0.46

 faſt

0.44

Activations Density 0.047%

terms associated with specific industries, medical conditions, or categories of items

No Comments

No Known Activations