INDEX

Explanations

phrases associated with surprising or unexpected outcomes

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

tagHelperRunner

-0.61

AddTagHelper

-0.57

قایناق‌لار

-0.53

 autorytatywna

-0.50

 متعلقه

-0.48

hoeddwyd

-0.47

Geograf

-0.45

hro

-0.45

 Linton

-0.45

hdysval

-0.45

POSITIVE LOGITS

 surprise

1.39

surprise

1.27

 surprised

1.26

 surprises

1.25

 unsur

1.24

 Surprise

1.24

Surprise

1.19

 surpresa

1.16

Surprised

1.15

 sorpresa

1.14

Activations Density 0.229%

phrases associated with surprising or unexpected outcomes

No Comments

No Known Activations