INDEX

Explanations

references to brands and branding

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Дереккөздер

-1.04

 Parigi

-0.95

 Cytometry

-0.89

 Watcher

-0.87

 Benoît

-0.85

 Deputies

-0.84

)_/¯

-0.83

 poème

-0.81

hmigung

-0.78

://$

-0.78

POSITIVE LOGITS

 brand

2.23

 BRAND

2.15

 brands

2.13

 Brand

2.12

brand

2.05

Brand

2.02

brands

1.98

BRAND

1.95

Brands

1.92

 Brands

1.85

Activations Density 0.020%

references to brands and branding

No Comments

No Known Activations