INDEX

Explanations

references to numerical values and calculations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

GraphicsUnit

-0.73

 Exactos

-0.71

\{\\

-0.71

 Waray

-0.70

 חיצוניים

-0.69

Filmografia

-0.69

 AppComponent

-0.68

UserScript

-0.68

Билгалдахарш

-0.67

Filmographie

-0.66

POSITIVE LOGITS

 متعلقه

0.50

↩

0.47

 marcha

0.47

าศ

0.46

хьтан

0.46

 wios

0.45

 parlato

0.45

stě

0.45

jul

0.45

fjspx

0.44

Activations Density 0.823%

references to numerical values and calculations

No Comments

No Known Activations