INDEX

Explanations

references to academic institutions and researchers

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

 synd

-0.46

dden

-0.45

 global

-0.42

trus

-0.41

@"/

-0.40

 Wikipedia

-0.40

arb

-0.40

 pratic

-0.40

 press

-0.39

Hou

-0.39

POSITIVE LOGITS

 ddelweddau

0.71

tagHelperRunner

0.68

 CreateTagHelper

0.67

 oamenii

0.67

 cadrul

0.67

 Wiktionnaire

0.65

 fermés

0.64

RenderAtEndOf

0.64

BeginContext

0.63

tagext

0.63

Activations Density 0.294%

references to academic institutions and researchers

No Comments

No Known Activations