INDEX

Explanations

specific phrases that indicate quality or classification within sets, particularly concerning characteristics of products or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

+#+#

-1.15

évaluateur

-1.11

:✨

-1.10

MigrationBuilder

-1.05

 CreateTagHelper

-1.01

WebElementEntity

-0.92

 Autorizaciones

-0.89

ValueStyle

-0.89

ForValue

-0.89

WriteTagHelper

-0.89

POSITIVE LOGITS

 form

0.63

 format

0.54

0.50

 bentuk

0.50

in

0.49

 formato

0.48

 forma

0.48

 formats

0.47

 collaboration

0.46

 detail

0.45

Activations Density 0.429%

specific phrases that indicate quality or classification within sets, particularly concerning characteristics of products or entities

No Comments

No Known Activations