INDEX

Explanations

statements expressing agreement or disagreement regarding beliefs and opinions, particularly in social contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

utie

-0.47

entials

-0.45

//

-0.45

foy

-0.45

MLLoader

-0.44

PMailer

-0.44

älde

-0.43

ptime

-0.43

#!/

-0.42



-0.41

POSITIVE LOGITS

 agree

3.10

 agrees

2.72

 Agree

2.60

 agreeing

2.59

 agreement

2.55

 agreed

2.55

agree

2.51

Agree

2.44

agreed

2.26

 Agreed

2.24

Activations Density 0.410%

statements expressing agreement or disagreement regarding beliefs and opinions, particularly in social contexts

No Comments

No Known Activations