INDEX

Explanations

terms associated with perception and awareness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

TestingModule

-0.93

 Meksiku

-0.90

 onOptions

-0.87

 Amon

-0.87

 SqlParameter

-0.85

awaiter

-0.85

IDATE

-0.84

Guys

-0.84

Története

-0.84

guys

-0.83

POSITIVE LOGITS

Eme

0.73

 gesto

0.69

IAP

0.69

 Eilish

0.68

 inflater

0.68

 surve

0.67

spe

0.66

ec

0.66

 BERNAMA

0.66

`.

0.66

Activations Density 0.251%

terms associated with perception and awareness

No Comments

No Known Activations