INDEX

Explanations

numerical representations, particularly in mathematical or statistical contexts

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

Some

-0.48

 Some

-0.46

 some

-0.44

تری

-0.41

IVEREF

-0.41

 qualche

-0.40

Demografie

-0.40

complexContent

-0.40

comuna

-0.40

rierung

-0.40

POSITIVE LOGITS

 half

0.77

half

0.75

 HALF

0.67

 Half

0.65

makeConstraints

0.65

HALF

0.65

Half

0.64

一半

0.64

 mezza

0.62

 mitad

0.61

Activations Density 0.482%

numerical representations, particularly in mathematical or statistical contexts

No Comments

No Known Activations