INDEX

Explanations

references to IBM and its related technologies or products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 καν

-0.68

 Vann

-0.67

 Humphreys

-0.66

 Barbier

-0.63

 Vign

-0.62

clist

-0.61

nicity

-0.61

Smy

-0.60

 확인함

-0.60

 boletín

-0.60

POSITIVE LOGITS

 Hitler

1.42

IBM

1.41

 Nike

1.40

 Toyota

1.34

 Boeing

1.32

 Microsoft

1.30

Nike

1.30

Microsoft

1.26

 Lenin

1.25

 Samsung

1.25

Activations Density 3.383%

references to IBM and its related technologies or products

No Comments

No Known Activations