INDEX

Explanations

words related to tasks, phone numbers, and product management

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 propOrder

-0.55

tabria

-0.49

JoinColumn

-0.47

 صوتيه

-0.47

 profundos

-0.45

TagHelpers

-0.45

 kilogram

-0.43

 Methuen

-0.43

省市镇

-0.42

nagar

-0.42

POSITIVE LOGITS

 nahilalakip

0.74

enumi

0.72

 виправивши

0.64

Enllaces

0.63

Życiorys

0.62

出版年

0.60

ViewFeatures

0.59

Legături

0.59

Viited

0.59

lgari

0.58

Activations Density 0.144%

words related to tasks, phone numbers, and product management

No Comments

No Known Activations