INDEX

Explanations

references to traits and qualities that indicate intelligence and competence

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

Connectors starting phrases or sentences

np_acts-logits-general · gemini-2.0-flash

judgment and caution

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 autorytatywna

-0.60

argout

-0.58

 mourut

-0.55

ⓘ

-0.54

 EClass

-0.53

Ragnar

-0.52

InitVars

-0.52

rungsseite

-0.49

AllowAnonymous

-0.48

 visibilidad

-0.48

POSITIVE LOGITS

 activity

0.65

UnusedPrivate

0.65

principalTable

0.65

 prompt

0.62

 alert

0.59

 promp

0.57

 pinulongan

0.57

 manly

0.57

 moderation

0.56

 firm

0.56

Activations Density 0.307%

references to traits and qualities that indicate intelligence and competence

Connectors starting phrases or sentences

judgment and caution

No Comments

No Known Activations