INDEX

Explanations

expressions of the concept of "lying" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

ραγ

-0.52

Starting

-0.51

 volto

-0.50

 caña

-0.48

 Kette

-0.48

aware

-0.47

-0.46

PREFIX

-0.46

 Starting

-0.46

 Briggs

-0.46

POSITIVE LOGITS

 lies

1.44

 lying

1.42

lie

1.29

Lying

1.27

 Lies

1.18

 Lying

1.15

 rests

1.10

 liggen

1.07

Lies

1.05

 liegen

1.03

Activations Density 0.191%

expressions of the concept of "lying" in various contexts

No Comments

No Known Activations