INDEX

Explanations

dialogue and conversational interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 ་་

-0.98

contentLoaded

-0.97

 myſelf

-0.95

 Monfieur

-0.95

 itſelf

-0.95

ſelves

-0.95

 ―――――

-0.93

Efq

-0.90

 raiſ

-0.88

 Majefty

-0.88

POSITIVE LOGITS

 soudain

0.63

 suddenly

0.62

0.55

 pulled

0.53

0.50

 said

0.49

jsxFileName

0.48

Bon

0.46

↵

0.45

Activations Density 0.267%

dialogue and conversational interactions

No Comments

No Known Activations