INDEX

Explanations

phrases related to problem-solving and addressing issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

featureID

-0.50

Jeografia

-0.46

 discussion

-0.44

Glück

-0.42

 surla

-0.42

 trebui

-0.41

Candidates

-0.41

 charts

-0.41

 restTemplate

-0.41

culada

-0.41

POSITIVE LOGITS

 longstanding

0.57

 maux

0.56

 perceived

0.53

 misconceptions

0.53

AndEndTag

0.51

 lingering

0.47

 recentes

0.47

 ills

0.46

 eventuali

0.45

 atuais

0.45

Activations Density 0.542%

phrases related to problem-solving and addressing issues

No Comments

No Known Activations