INDEX

Explanations

references to font-related terminology in written content

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

Sucesor

-0.87

 propOrder

-0.84

 EconPapers

-0.84

onViewCreated

-0.80

+#+#

-0.80

AsUp

-0.78

routeProvider

-0.76

onAttach

-0.75

Aiheesta

-0.74

'])){

-0.74

POSITIVE LOGITS

font

2.44

 font

2.28

 Font

2.01

 FONT

1.97

Font

1.95

 fonts

1.77

FONT

1.69

 Fonts

1.67

fonts

1.54

 Fontana

1.36

Activations Density 0.047%

references to font-related terminology in written content

No Comments

No Known Activations