INDEX

Explanations

references to trained professionals and their roles in providing services

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

 initComponents

-0.61

 BoxFit

-0.52

RTEE

-0.51

istocene

-0.48

sonaro

-0.48

WindowConstants

-0.47

seigneur

-0.47

getStringExtra

-0.46

createCanvas

-0.46

Espèce

-0.46

POSITIVE LOGITS

 experts

0.73

 expertise

0.65

 expert

0.64

 trained

0.63

 esperti

0.59

 expertos

0.58

 specialists

0.58

 knowledgeable

0.57

 staff

0.56

 skilled

0.56

Activations Density 0.261%

references to trained professionals and their roles in providing services

No Comments

No Known Activations