INDEX

Explanations

proper nouns or names associated with individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

évaluateur

-0.69

发表于

-0.65

LookAnd

-0.60

bootstrapcdn

-0.53

"]();

-0.51

 utafitiHapana

-0.48

──

-0.48

cal

-0.47

")[

-0.45

WaitGroup

-0.45

POSITIVE LOGITS

 AspNetCore

0.77

}{@

0.75

RTDA

0.73

 henvisninger

0.71

 wikipagina

0.68

RTEE

0.67

دانشنامهٔ

0.66

 purpoſe

0.62

 незавершена

0.62

(&:

0.61

Activations Density 0.123%

proper nouns or names associated with individuals

No Comments

No Known Activations