INDEX

Explanations

references to positive features or qualities of entities or experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

EndGlobalSection

-0.48

 rospy

-0.46

 NSCoder

-0.45

 imageNamed

-0.44

gdx

-0.44

flashdata

-0.44

 syno

-0.41

yar

-0.40

 UIAlert

-0.39

 gefe

-0.39

POSITIVE LOGITS

 immerhin

0.70

SequentialGroup

0.66

 nice

0.65

__*/

0.64

 thiện

0.62

Semoga

0.61

enumi

0.60

 reasonably

0.59

 непло

0.59

/}.

0.59

Activations Density 0.334%

references to positive features or qualities of entities or experiences

No Comments

No Known Activations