INDEX

Explanations

terms related to evaluation frameworks and assessments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

usammen

-0.67

 Wikimedijinoj

-0.62

ípios

-0.55

UnifiedTopology

-0.55

othelioma

-0.52

yntaxException

-0.52

 chup

-0.52

 haystack

-0.51

ruptedException

-0.51

UnknownFieldSet

-0.51

POSITIVE LOGITS

 rating

1.34

 category

1.32

 classification

1.28

 rated

1.27

 Category

1.25

 grade

1.24

 Grade

1.15

 kategori

1.15

 classifications

1.15

 ratings

1.12

Activations Density 1.144%

terms related to evaluation frameworks and assessments

No Comments

No Known Activations