INDEX

Explanations

phrases related to personal beliefs and moral dilemmas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

Efq

-1.07

 houſe

-1.04

 purpoſe

-1.01

 Jefus

-1.01

 Majefty

-1.00

 Monfieur

-0.98

 pleaſure

-0.98

 ſta

-0.97

 himſelf

-0.92

 myſelf

-0.92

POSITIVE LOGITS

my

0.55

0.48

isn

0.47

 that

0.46

0.45

cre

0.43

die

0.43

no

0.42

 human

0.42

Activations Density 2.655%

phrases related to personal beliefs and moral dilemmas

No Comments

No Known Activations