INDEX

Explanations

occurrences of the word "lie" 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 @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

wezen

-0.57

addPreferredGap

-0.55

 pequ

-0.55

 Dernière

-0.53

 gezogen

-0.52

DotNetBar

-0.52

zubauen

-0.51

Gemeinden

-0.51

ovsky

-0.50

րջ

-0.50

POSITIVE LOGITS

lie

4.46

Lie

3.56

Lie

3.36

LIE

3.32

lie

3.09

 lies

2.63

LIE

2.59

 lying

2.57

 Lying

2.43

 lied

2.35

Activations Density 0.074%

occurrences of the word "lie" in various contexts

No Comments

No Known Activations