INDEX

Explanations

affirmations and confirmations in responses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 bezeichneter

-0.47

Espèce

-0.46

diğinde

-0.46

ⓘ

-0.46

}`).

-0.41

χν

-0.41

 rotation

-0.41

 Parad

-0.41

::::::::

-0.40

 prata

-0.40

POSITIVE LOGITS

 GenerationType

0.84

 فريبيس

0.77

 kasarigan

0.76

yes

0.75

 Nope

0.74

Yes

0.69

SPATH

0.67

ropoda

0.66

QRect

0.66

 resourceCulture

0.65

Activations Density 0.349%

affirmations and confirmations in responses

No Comments

No Known Activations