INDEX

Explanations

mentions of the name "Sha."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

躇

-0.69

 NgModule

-0.67

 isInitialized

-0.65

 betweenstory

-0.64

Och

-0.63

 Plin

-0.60

tagHelperRunner

-0.59

 Wikimédia

-0.59

 Schiff

-0.59

 LoginComponent

-0.58

POSITIVE LOGITS

Sha

4.27

Sha

4.08

sha

3.54

sha

3.46

SHA

2.51

SHA

2.18

 Shak

1.97

 shave

1.70

 shaving

1.70

 Shaker

1.69

Activations Density 0.069%

mentions of the name "Sha."

No Comments

No Known Activations