INDEX

Explanations

phrases indicating future events or anticipated outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/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.19.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

 ivelany

-0.55

 ligiloj

-0.51

jaros

-0.50

bzero

-0.47

---*/

-0.46

rofoam

-0.45

 AssemblyCulture

-0.44

 hochzeit

-0.44

bbons

-0.44

igrette

-0.43

POSITIVE LOGITS

 sometime

1.53

 Sometime

1.36

 early

1.27

 late

1.16

 earliest

1.16

early

1.09

 somewhere

1.06

 sooner

1.02

 probably

1.02

 soon

1.02

Activations Density 0.326%

phrases indicating future events or anticipated outcomes

No Comments

No Known Activations