INDEX

Explanations

phrases related to requests or asking for information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

AfterClass

-0.75

 dalamnya

-0.71

 SetUp

-0.66

ίων

-0.65

Kl

-0.63

hien

-0.62

 battre

-0.62

AfterViewInit

-0.61

 Rowling

-0.60

isConnected

-0.60

POSITIVE LOGITS

 request

3.13

 requests

2.94

 Request

2.89

 REQUEST

2.67

 requested

2.65

request

2.63

 Requests

2.61

Request

2.55

REQUEST

2.48

 requesting

2.44

Activations Density 0.065%

phrases related to requests or asking for information

No Comments

No Known Activations