INDEX

Explanations

mentions of firms or companies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Kela

-0.69

이션

-0.69

eken

-0.68

apas

-0.67

HUN

-0.65

TAL

-0.65

ανά

-0.64

Aval

-0.64

 وعلى

-0.63

"))

-0.63

POSITIVE LOGITS

Firm

2.38

 firm

2.38

 Firm

2.38

 Firms

2.34

firm

2.32

 firms

2.27

 FIRM

2.12

Fir

1.72

 firme

1.64

 firmer

1.46

Activations Density 0.067%

mentions of firms or companies

No Comments

No Known Activations