INDEX

Explanations

phrases indicating uncertainty or conditionality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 <<<<<<<<<<<<<<

-0.78



-0.66

yyr

-0.62

jspb

-0.62

UnsafeEnabled

-0.52

Descripció

-0.52

 coating

-0.52

 Coating

-0.50

 saites

-0.50

haikusbot

-0.49

POSITIVE LOGITS

the

0.64

 việc

0.47

it

0.45

 chociaż

0.43

ailleurs

0.43

 fédé

0.43

่านั้น

0.42

 Tatsache

0.42

ciaż

0.41

omiast

0.41

Activations Density 0.431%

phrases indicating uncertainty or conditionality

No Comments

No Known Activations