INDEX

Explanations

phrases emphasizing relationships and connections within 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

社

-0.52

giphy

-0.50

getMessage

-0.47

taf

-0.46

 Perse

-0.44

mens

-0.44

Pg

-0.44

分

-0.44

انو

-0.44

 nico

-0.43

POSITIVE LOGITS

ⓘ

0.95

 esternos

0.82

WebControls

0.82

Hauptartikel

0.81

ειτουργ

0.78

 AssemblyTitle

0.77

WriteTagHelper

0.76

 ciasc

0.75

 ciascuno

0.73

 ویکی‌پدی

0.73

Activations Density 0.920%

phrases emphasizing relationships and connections within contexts

No Comments

No Known Activations