INDEX

Explanations

questions or statements related to issues, concerns, or inquiries

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

🫶

-0.56

 McCormack

-0.55

TestTools

-0.55

 Blitz

-0.54

Geplaatst

-0.54

 binder

-0.53

 McKinnon

-0.53

 Corbett

-0.53

onBlur

-0.53

/.../

-0.53

POSITIVE LOGITS

whats

1.29

Whats

1.22

 Whats

1.17

 whats

1.02

WHAT

0.81

 WHAT

0.79

ValueGenerated

0.77

 What

0.76

what

0.76

What

0.73

Activations Density 0.081%

questions or statements related to issues, concerns, or inquiries

No Comments

No Known Activations