INDEX

Explanations

expressions of emotional responses and contemplations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

felves

-0.76

Personensuche

-0.73

 utafitiHapana

-0.69

 himſelf

-0.69

нодоро

-0.68

ectoria

-0.67

iconque

-0.66

tersebut

-0.66

μως

-0.66

újo

-0.66

POSITIVE LOGITS

ąg

0.54

You

0.53

oh

0.53

You

0.52

 ostavi

0.51

du

0.48

رب

0.48

х

0.47

Go

0.47

Activations Density 0.300%

expressions of emotional responses and contemplations

No Comments

No Known Activations