INDEX

Explanations

phrases that indicate personal responsibility or suggestions for action

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

الحياه

-0.83

UnusedPrivate

-0.54

 henkilö

-0.52

 EconPapers

-0.52

 cotone

-0.51

rzost

-0.51

 Sabina

-0.50

الدراسه

-0.49

 näytte

-0.48

 tournant

-0.48

POSITIVE LOGITS

Chooser

0.69

 متعلقه

0.67

 hurry

0.60

脚注の使い方

0.58

 devriez

0.56

 Pretty

0.55

 PROCEED

0.53

mtd

0.53

 widerrufen

0.52

 should

0.51

Activations Density 0.221%

phrases that indicate personal responsibility or suggestions for action

No Comments

No Known Activations