INDEX

Explanations

key terms and phrases related to complex ideas and situations involving communication, social interactions, and nuanced contexts

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 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

 ochran

-0.33

록

-0.32

setcounter

-0.32

 alami

-0.32

 hadn

-0.31

Enllaces

-0.31

 Monteiro

-0.30

 Armstrong

-0.30

AndEndTag

-0.30

endforeach

-0.30

POSITIVE LOGITS

expandindo

0.78

ロウィン

0.70

parsedMessage

0.62

DeleteBehavior

0.61

TestingModule

0.60

 IFTT

0.59

AISSEE

0.59

 виправивши

0.58

évaluateur

0.58

 ſind

0.58

Activations Density 1.399%

key terms and phrases related to complex ideas and situations involving communication, social interactions, and nuanced contexts

No Comments

No Known Activations