INDEX

Explanations

conversational phrases questioning someone's beliefs or statements

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 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

djangoproject

-0.63

colgroup

-0.50

}.

-0.50

tagHelper

-0.49

wpdb

-0.49

!*\

-0.46

 intptr

-0.46

merkungen

-0.45

arakhand

-0.43

значно

-0.43

POSITIVE LOGITS

 Stop

1.29

 stop

1.25

Stop

1.22

why

1.18

 STOP

1.08

stop

1.06

Why

1.05

why

1.04

Why

0.99

wtf

0.96

Activations Density 0.306%

conversational phrases questioning someone's beliefs or statements

No Comments

No Known Activations