INDEX

Explanations

questions or inquiries related to specific subjects or scenarios

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

lamabad

-0.63

</caption>

-0.55

цезда

-0.55

abinieri

-0.54

makeText

-0.53

 hObject

-0.52

,:]

-0.51

kmäler

-0.51

ecraft

-0.50

]='\

-0.50

POSITIVE LOGITS

 Does

2.41

 does

2.38

Does

2.35

did

2.05

Did

2.01

Are

1.96

does

1.95

Did

1.91

Are

1.89

Is

1.87

Activations Density 1.415%

questions or inquiries related to specific subjects or scenarios

No Comments

No Known Activations