INDEX

Explanations

references to expressions of gratitude and acknowledgment in research contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

MigrationBuilder

-0.75

ModelSerializer

-0.74

Personendaten

-0.68

 Numerade

-0.66

 Савезне

-0.64

 poveznice

-0.62

queryInterface

-0.61

weder

-0.61

AddTagHelper

-0.61

sstil

-0.61

POSITIVE LOGITS

 ochi

0.47

Obrigado

0.45

 obicei

0.45

 maravilh

0.44

 Tasche

0.44

一路

0.43

Kindly

0.41

 Kindly

0.41

EndInit

0.41

my

0.41

Activations Density 0.354%

references to expressions of gratitude and acknowledgment in research contexts

No Comments

No Known Activations